ICCV 2025 Open Access Repository

Papers

Back
Efficient Adaptation of Pre-trained Vision Transformer underpinned by Approximately Orthogonal Fine-Tuning Strategy: Yiting Yang,

Hao Luo,

Yuan Sun,

Qingsen Yan,

Haokui Zhang,

Wei Dong,

Guoqing Wang,

Peng Wang,

Yang Yang,

Hengtao Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Yiting and Luo, Hao and Sun, Yuan and Yan, Qingsen and Zhang, Haokui and Dong, Wei and Wang, Guoqing and Wang, Peng and Yang, Yang and Shen, Hengtao}, title = {Efficient Adaptation of Pre-trained Vision Transformer underpinned by Approximately Orthogonal Fine-Tuning Strategy}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4878-4887} }
MM-IFEngine: Towards Multimodal Instruction Following: Shengyuan Ding,

Shenxi Wu,

Xiangyu Zhao,

Yuhang Zang,

Haodong Duan,

Xiaoyi Dong,

Pan Zhang,

Yuhang Cao,

Dahua Lin,

Jiaqi Wang; [pdf] [supp]
[bibtex]
@InProceedings{Ding_2025_ICCV, author = {Ding, Shengyuan and Wu, Shenxi and Zhao, Xiangyu and Zang, Yuhang and Duan, Haodong and Dong, Xiaoyi and Zhang, Pan and Cao, Yuhang and Lin, Dahua and Wang, Jiaqi}, title = {MM-IFEngine: Towards Multimodal Instruction Following}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1099-1109} }
ROADWork: A Dataset and Benchmark for Learning to Recognize, Observe, Analyze and Drive Through Work Zones: Anurag Ghosh,

Shen Zheng,

Robert Tamburo,

Khiem Vuong,

Juan Alvarez-Padilla,

Hailiang Zhu,

Michael Cardei,

Nicholas Dunn,

Christoph Mertz,

Srinivasa G. Narasimhan; [pdf] [supp]
[bibtex]
@InProceedings{Ghosh_2025_ICCV, author = {Ghosh, Anurag and Zheng, Shen and Tamburo, Robert and Vuong, Khiem and Alvarez-Padilla, Juan and Zhu, Hailiang and Cardei, Michael and Dunn, Nicholas and Mertz, Christoph and Narasimhan, Srinivasa G.}, title = {ROADWork: A Dataset and Benchmark for Learning to Recognize, Observe, Analyze and Drive Through Work Zones}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6132-6142} }
Gradient Decomposition and Alignment for Incremental Object Detection: Wenlong Luo,

Shizhou Zhang,

De Cheng,

Yinghui Xing,

Guoqiang Liang,

Peng Wang,

Yanning Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Luo_2025_ICCV, author = {Luo, Wenlong and Zhang, Shizhou and Cheng, De and Xing, Yinghui and Liang, Guoqiang and Wang, Peng and Zhang, Yanning}, title = {Gradient Decomposition and Alignment for Incremental Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4486-4495} }
Gradient Extrapolation for Debiased Representation Learning: Ihab Asaad,

Maha Shadaydeh,

Joachim Denzler; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Asaad_2025_ICCV, author = {Asaad, Ihab and Shadaydeh, Maha and Denzler, Joachim}, title = {Gradient Extrapolation for Debiased Representation Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3819-3829} }
Improving Large Vision and Language Models by Learning from a Panel of Peers: Jefferson Hernandez,

Jing Shi,

Simon Jenni,

Vicente Ordonez,

Kushal Kafle; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hernandez_2025_ICCV, author = {Hernandez, Jefferson and Shi, Jing and Jenni, Simon and Ordonez, Vicente and Kafle, Kushal}, title = {Improving Large Vision and Language Models by Learning from a Panel of Peers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1402-1412} }
Federated Representation Angle Learning: Liping Yi,

Han Yu,

Gang Wang,

Xiaoguang Liu,

Xiaoxiao Li; [pdf]
[bibtex]
@InProceedings{Yi_2025_ICCV, author = {Yi, Liping and Yu, Han and Wang, Gang and Liu, Xiaoguang and Li, Xiaoxiao}, title = {Federated Representation Angle Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1314-1324} }
Why LVLMs Are More Prone to Hallucinations in Longer Responses: The Role of Context: Ge Zheng,

Jiaye Qian,

Jiajin Tang,

Sibei Yang; [pdf] [supp]
[bibtex]
@InProceedings{Zheng_2025_ICCV, author = {Zheng, Ge and Qian, Jiaye and Tang, Jiajin and Yang, Sibei}, title = {Why LVLMs Are More Prone to Hallucinations in Longer Responses: The Role of Context}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4101-4113} }
Training-Free Personalization via Retrieval and Reasoning on Fingerprints: Deepayan Das,

Davide Talon,

Yiming Wang,

Massimiliano Mancini,

Elisa Ricci; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Das_2025_ICCV, author = {Das, Deepayan and Talon, Davide and Wang, Yiming and Mancini, Massimiliano and Ricci, Elisa}, title = {Training-Free Personalization via Retrieval and Reasoning on Fingerprints}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9683-9692} }
VisionMath: Vision-Form Mathematical Problem-Solving: Zongyang Ma,

Yuxin Chen,

Ziqi Zhang,

Zhongang Qi,

Chunfeng Yuan,

Shaojie Zhu,

Chengxiang Zhuo,

Bing Li,

Ye Liu,

Zang Li,

Ying Shan,

Weiming Hu; [pdf] [supp]
[bibtex]
@InProceedings{Ma_2025_ICCV, author = {Ma, Zongyang and Chen, Yuxin and Zhang, Ziqi and Qi, Zhongang and Yuan, Chunfeng and Zhu, Shaojie and Zhuo, Chengxiang and Li, Bing and Liu, Ye and Li, Zang and Shan, Ying and Hu, Weiming}, title = {VisionMath: Vision-Form Mathematical Problem-Solving}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1162-1172} }
CWNet: Causal Wavelet Network for Low-Light Image Enhancement: Tongshun Zhang,

Pingping Liu,

Yubing Lu,

Mengen Cai,

Zijian Zhang,

Zhe Zhang,

Qiuzhan Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Tongshun and Liu, Pingping and Lu, Yubing and Cai, Mengen and Zhang, Zijian and Zhang, Zhe and Zhou, Qiuzhan}, title = {CWNet: Causal Wavelet Network for Low-Light Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8789-8799} }
CoA-VLA: Improving Vision-Language-Action Models via Visual-Text Chain-of-Affordance: Jinming Li,

Yichen Zhu,

Zhibin Tang,

Junjie Wen,

Minjie Zhu,

Xiaoyu Liu,

Chengmeng Li,

Ran Cheng,

Yaxin Peng,

Yan Peng,

Feifei Feng; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Jinming and Zhu, Yichen and Tang, Zhibin and Wen, Junjie and Zhu, Minjie and Liu, Xiaoyu and Li, Chengmeng and Cheng, Ran and Peng, Yaxin and Peng, Yan and Feng, Feifei}, title = {CoA-VLA: Improving Vision-Language-Action Models via Visual-Text Chain-of-Affordance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9759-9769} }
Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection: Subhajit Maity,

Ayan Kumar Bhunia,

Subhadeep Koley,

Pinaki Nath Chowdhury,

Aneeshan Sain,

Yi-Zhe Song; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Maity_2025_ICCV, author = {Maity, Subhajit and Bhunia, Ayan Kumar and Koley, Subhadeep and Chowdhury, Pinaki Nath and Sain, Aneeshan and Song, Yi-Zhe}, title = {Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {284-296} }
Open-Vocabulary Octree-Graph for 3D Scene Understanding: Zhigang Wang,

Yifei Su,

Chenhui Li,

Dong Wang,

Yan Huang,

Xuelong Li,

Bin Zhao; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Zhigang and Su, Yifei and Li, Chenhui and Wang, Dong and Huang, Yan and Li, Xuelong and Zhao, Bin}, title = {Open-Vocabulary Octree-Graph for 3D Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7037-7047} }
Head2Body: Body Pose Generation from Multi-sensory Head-mounted Inputs: Minh Tran,

Hongda Mao,

Qingshuang Chen,

Yelin Kim; [pdf] [supp]
[bibtex]
@InProceedings{Tran_2025_ICCV, author = {Tran, Minh and Mao, Hongda and Chen, Qingshuang and Kim, Yelin}, title = {Head2Body: Body Pose Generation from Multi-sensory Head-mounted Inputs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6849-6858} }
Closed-Loop Transfer for Weakly-supervised Affordance Grounding: Jiajin Tang,

Zhengxuan Wei,

Ge Zheng,

Sibei Yang; [pdf]
[bibtex]
@InProceedings{Tang_2025_ICCV, author = {Tang, Jiajin and Wei, Zhengxuan and Zheng, Ge and Yang, Sibei}, title = {Closed-Loop Transfer for Weakly-supervised Affordance Grounding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9530-9539} }
Zeroth-Order Fine-Tuning of LLMs in Random Subspaces: Ziming Yu,

Pan Zhou,

Sike Wang,

Jia Li,

Mi Tian,

Hua Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2025_ICCV, author = {Yu, Ziming and Zhou, Pan and Wang, Sike and Li, Jia and Tian, Mi and Huang, Hua}, title = {Zeroth-Order Fine-Tuning of LLMs in Random Subspaces}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4475-4485} }
G2D: Boosting Multimodal Learning with Gradient-Guided Distillation: Mohammed Rakib,

Arunkumar Bagavathi; [pdf] [supp]
[bibtex]
@InProceedings{Rakib_2025_ICCV, author = {Rakib, Mohammed and Bagavathi, Arunkumar}, title = {G2D: Boosting Multimodal Learning with Gradient-Guided Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4059-4068} }
PAN-Crafter: Learning Modality-Consistent Alignment for PAN-Sharpening: Jeonghyeok Do,

Sungpyo Kim,

Geunhyuk Youk,

Jaehyup Lee,

Munchurl Kim; [pdf] [supp]
[bibtex]
@InProceedings{Do_2025_ICCV, author = {Do, Jeonghyeok and Kim, Sungpyo and Youk, Geunhyuk and Lee, Jaehyup and Kim, Munchurl}, title = {PAN-Crafter: Learning Modality-Consistent Alignment for PAN-Sharpening}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4242-4252} }
Rethinking Few Shot CLIP Benchmarks: A Critical Analysis in the Inductive Setting: Alexey Kravets,

Da Chen,

Vinay P. Namboodiri; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kravets_2025_ICCV, author = {Kravets, Alexey and Chen, Da and Namboodiri, Vinay P.}, title = {Rethinking Few Shot CLIP Benchmarks: A Critical Analysis in the Inductive Setting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1902-1911} }
GSOT3D: Towards Generic 3D Single Object Tracking in the Wild: Yifan Jiao,

Yunhao Li,

Junhua Ding,

Qing Yang,

Song Fu,

Heng Fan,

Libo Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiao_2025_ICCV, author = {Jiao, Yifan and Li, Yunhao and Ding, Junhua and Yang, Qing and Fu, Song and Fan, Heng and Zhang, Libo}, title = {GSOT3D: Towards Generic 3D Single Object Tracking in the Wild}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5469-5478} }
What You Have is What You Track: Adaptive and Robust Multimodal Tracking: Yuedong Tan,

Jiawei Shao,

Eduard Zamfir,

Ruanjun Li,

Zhaochong An,

Chao Ma,

Danda Paudel,

Luc Van Gool,

Radu Timofte,

Zongwei Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tan_2025_ICCV, author = {Tan, Yuedong and Shao, Jiawei and Zamfir, Eduard and Li, Ruanjun and An, Zhaochong and Ma, Chao and Paudel, Danda and Van Gool, Luc and Timofte, Radu and Wu, Zongwei}, title = {What You Have is What You Track: Adaptive and Robust Multimodal Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3455-3465} }
Generative Zoo: Tomasz Niewiadomski,

Anastasios Yiannakidis,

Hanz Cuevas-Velasquez,

Soubhik Sanyal,

Michael J. Black,

Silvia Zuffi,

Peter Kulits; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Niewiadomski_2025_ICCV, author = {Niewiadomski, Tomasz and Yiannakidis, Anastasios and Cuevas-Velasquez, Hanz and Sanyal, Soubhik and Black, Michael J. and Zuffi, Silvia and Kulits, Peter}, title = {Generative Zoo}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8492-8502} }
Any-SSR: How Recursive Least Squares Works in Continual Learning of Large Language Model: Kai Tong,

Kang Pan,

Xiao Zhang,

Erli Meng,

Run He,

Yawen Cui,

Nuoyan Guo,

Huiping Zhuang; [pdf] [supp]
[bibtex]
@InProceedings{Tong_2025_ICCV, author = {Tong, Kai and Pan, Kang and Zhang, Xiao and Meng, Erli and He, Run and Cui, Yawen and Guo, Nuoyan and Zhuang, Huiping}, title = {Any-SSR: How Recursive Least Squares Works in Continual Learning of Large Language Model}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3047-3057} }
Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs: Zitian Wang,

Yue Liao,

Kang Rong,

Fengyun Rao,

Yibo Yang,

Si Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Zitian and Liao, Yue and Rong, Kang and Rao, Fengyun and Yang, Yibo and Liu, Si}, title = {Instruction-Oriented Preference Alignment for Enhancing Multi-Modal Comprehension Capability of MLLMs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2010-2021} }
SFUOD: Source-Free Unknown Object Detection: Keon-Hee Park,

Seun-An Choe,

Gyeong-Moon Park; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2025_ICCV, author = {Park, Keon-Hee and Choe, Seun-An and Park, Gyeong-Moon}, title = {SFUOD: Source-Free Unknown Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3499-3508} }
ToolVQA: A Dataset for Multi-step Reasoning VQA with External Tools: Shaofeng Yin,

Ting Lei,

Yang Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yin_2025_ICCV, author = {Yin, Shaofeng and Lei, Ting and Liu, Yang}, title = {ToolVQA: A Dataset for Multi-step Reasoning VQA with External Tools}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4424-4433} }
Information-Bottleneck Driven Binary Neural Network for Change Detection: Kaijie Yin,

Zhiyuan Zhang,

Shu Kong,

Tian Gao,

Cheng-Zhong Xu,

Hui Kong; [pdf] [arXiv]
[bibtex]
@InProceedings{Yin_2025_ICCV, author = {Yin, Kaijie and Zhang, Zhiyuan and Kong, Shu and Gao, Tian and Xu, Cheng-Zhong and Kong, Hui}, title = {Information-Bottleneck Driven Binary Neural Network for Change Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7176-7186} }
Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness: Haochen Wang,

Yucheng Zhao,

Tiancai Wang,

Haoqiang Fan,

Xiangyu Zhang,

Zhaoxiang Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Haochen and Zhao, Yucheng and Wang, Tiancai and Fan, Haoqiang and Zhang, Xiangyu and Zhang, Zhaoxiang}, title = {Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9275-9286} }
Dataset Ownership Verification for Pre-trained Masked Models: Yuechen Xie,

Jie Song,

Yicheng Shan,

Xiaoyan Zhang,

Yuanyu Wan,

Shengxuming Zhang,

Jiarui Duan,

Mingli Song; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xie_2025_ICCV, author = {Xie, Yuechen and Song, Jie and Shan, Yicheng and Zhang, Xiaoyan and Wan, Yuanyu and Zhang, Shengxuming and Duan, Jiarui and Song, Mingli}, title = {Dataset Ownership Verification for Pre-trained Masked Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3132-3142} }
Language Driven Occupancy Prediction: Zhu Yu,

Bowen Pang,

Lizhe Liu,

Runmin Zhang,

Qiang Li,

Si-Yuan Cao,

Maochun Luo,

Mingxia Chen,

Sheng Yang,

Hui-Liang Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2025_ICCV, author = {Yu, Zhu and Pang, Bowen and Liu, Lizhe and Zhang, Runmin and Li, Qiang and Cao, Si-Yuan and Luo, Maochun and Chen, Mingxia and Yang, Sheng and Shen, Hui-Liang}, title = {Language Driven Occupancy Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7548-7558} }
Event-based Tiny Object Detection: A Benchmark Dataset and Baseline: Nuo Chen,

Chao Xiao,

Yimian Dai,

Shiman He,

Miao Li,

Wei An; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Nuo and Xiao, Chao and Dai, Yimian and He, Shiman and Li, Miao and An, Wei}, title = {Event-based Tiny Object Detection: A Benchmark Dataset and Baseline}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7209-7218} }
ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition: Ronggang Huang,

Haoxin Yang,

Yan Cai,

Xuemiao Xu,

Huaidong Zhang,

Shengfeng He; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2025_ICCV, author = {Huang, Ronggang and Yang, Haoxin and Cai, Yan and Xu, Xuemiao and Zhang, Huaidong and He, Shengfeng}, title = {ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9726-9736} }
FDPT: Federated Discrete Prompt Tuning for Black-Box Visual-Language Models: Jiaqi Wu,

Simin Chen,

Jing Tang,

Yuzhe Yang,

Yiming Chen,

Lixu Wang,

Song Lin,

Zehua Wang,

Wei Chen,

Zijian Tian; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2025_ICCV, author = {Wu, Jiaqi and Chen, Simin and Tang, Jing and Yang, Yuzhe and Chen, Yiming and Wang, Lixu and Lin, Song and Wang, Zehua and Chen, Wei and Tian, Zijian}, title = {FDPT: Federated Discrete Prompt Tuning for Black-Box Visual-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2461-2470} }
CE-FAM: Concept-Based Explanation via Fusion of Activation Maps: Michihiro Kuroki,

Toshihiko Yamasaki; [pdf]
[bibtex]
@InProceedings{Kuroki_2025_ICCV, author = {Kuroki, Michihiro and Yamasaki, Toshihiko}, title = {CE-FAM: Concept-Based Explanation via Fusion of Activation Maps}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1413-1422} }
PLAN: Proactive Low-Rank Allocation for Continual Learning: Xiequn Wang,

Zhan Zhuang,

Yu Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Xiequn and Zhuang, Zhan and Zhang, Yu}, title = {PLAN: Proactive Low-Rank Allocation for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2909-2918} }
EMoTive: Event-guided Trajectory Modeling for 3D Motion Estimation: Zengyu Wan,

Wei Zhai,

Yang Cao,

Zhengjun Zha; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wan_2025_ICCV, author = {Wan, Zengyu and Zhai, Wei and Cao, Yang and Zha, Zhengjun}, title = {EMoTive: Event-guided Trajectory Modeling for 3D Motion Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9342-9351} }
From Sharp to Blur: Unsupervised Domain Adaptation for 2D Human Pose Estimation Under Extreme Motion Blur Using Event Cameras: Youngho Kim,

Hoonhee Cho,

Kuk-Jin Yoon; [pdf] [arXiv]
[bibtex]
@InProceedings{Kim_2025_ICCV, author = {Kim, Youngho and Cho, Hoonhee and Yoon, Kuk-Jin}, title = {From Sharp to Blur: Unsupervised Domain Adaptation for 2D Human Pose Estimation Under Extreme Motion Blur Using Event Cameras}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9406-9417} }
Motal: Unsupervised 3D Object Detection by Modality and Task-specific Knowledge Transfer: Hai Wu,

Hongwei Lin,

Xusheng Guo,

Xin Li,

Mingming Wang,

Cheng Wang,

Chenglu Wen; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2025_ICCV, author = {Wu, Hai and Lin, Hongwei and Guo, Xusheng and Li, Xin and Wang, Mingming and Wang, Cheng and Wen, Chenglu}, title = {Motal: Unsupervised 3D Object Detection by Modality and Task-specific Knowledge Transfer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6284-6293} }
RetinexMCNet: A Memory Controller Dominated Network for Low-Light Video Enhancement Based on Retinex: Meiao Wang,

Xuejing Kang,

Yaxi Lu,

Jie Xu; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Meiao and Kang, Xuejing and Lu, Yaxi and Xu, Jie}, title = {RetinexMCNet: A Memory Controller Dominated Network for Low-Light Video Enhancement Based on Retinex}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9716-9725} }
Learnable Fractional Reaction-Diffusion Dynamics for Under-Display ToF Imaging and Beyond: Xin Qiao,

Matteo Poggi,

Xing Wei,

Pengchao Deng,

Yanhui Zhou,

Stefano Mattoccia; [pdf] [supp]
[bibtex]
@InProceedings{Qiao_2025_ICCV, author = {Qiao, Xin and Poggi, Matteo and Wei, Xing and Deng, Pengchao and Zhou, Yanhui and Mattoccia, Stefano}, title = {Learnable Fractional Reaction-Diffusion Dynamics for Under-Display ToF Imaging and Beyond}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6080-6090} }
Integrating Visual Interpretation and Linguistic Reasoning for Geometric Problem Solving: Zixian Guo,

Ming Liu,

Qilong Wang,

Zhilong Ji,

Jinfeng Bai,

Lei Zhang,

Wangmeng Zuo; [pdf] [supp]
[bibtex]
@InProceedings{Guo_2025_ICCV, author = {Guo, Zixian and Liu, Ming and Wang, Qilong and Ji, Zhilong and Bai, Jinfeng and Zhang, Lei and Zuo, Wangmeng}, title = {Integrating Visual Interpretation and Linguistic Reasoning for Geometric Problem Solving}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3988-3998} }
Dual-Rate Dynamic Teacher for Source-Free Domain Adaptive Object Detection: Qi He,

Xiao Wu,

Jun-Yan He,

Shuai Li; [pdf]
[bibtex]
@InProceedings{He_2025_ICCV, author = {He, Qi and Wu, Xiao and He, Jun-Yan and Li, Shuai}, title = {Dual-Rate Dynamic Teacher for Source-Free Domain Adaptive Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2067-2076} }
How Do Multimodal Large Language Models Handle Complex Multimodal Reasoning? Placing Them in An Extensible Escape Game: Ziyue Wang,

Yurui Dong,

Fuwen Luo,

Minyuan Ruan,

Zhili Cheng,

Chi Chen,

Peng Li,

Yang Liu; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Ziyue and Dong, Yurui and Luo, Fuwen and Ruan, Minyuan and Cheng, Zhili and Chen, Chi and Li, Peng and Liu, Yang}, title = {How Do Multimodal Large Language Models Handle Complex Multimodal Reasoning? Placing Them in An Extensible Escape Game}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4807-4817} }
UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling: Peiming Li,

Ziyi Wang,

Yulin Yuan,

Hong Liu,

Xiangming Meng,

Junsong Yuan,

Mengyuan Liu; [pdf]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Peiming and Wang, Ziyi and Yuan, Yulin and Liu, Hong and Meng, Xiangming and Yuan, Junsong and Liu, Mengyuan}, title = {UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6738-6747} }
PropVG: End-to-End Proposal-Driven Visual Grounding with Multi-Granularity Discrimination: Ming Dai,

Wenxuan Cheng,

Jiedong Zhuang,

Jiang-jiang Liu,

Hongshen Zhao,

Zhenhua Feng,

Wankou Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dai_2025_ICCV, author = {Dai, Ming and Cheng, Wenxuan and Zhuang, Jiedong and Liu, Jiang-jiang and Zhao, Hongshen and Feng, Zhenhua and Yang, Wankou}, title = {PropVG: End-to-End Proposal-Driven Visual Grounding with Multi-Granularity Discrimination}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7058-7068} }
Learning Visual Proxy for Compositional Zero-Shot Learning: Shiyu Zhang,

Cheng Yan,

Yang Liu,

Chenchen Jing,

Lei Zhou,

Wenjun Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Shiyu and Yan, Cheng and Liu, Yang and Jing, Chenchen and Zhou, Lei and Wang, Wenjun}, title = {Learning Visual Proxy for Compositional Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2793-2802} }
UPRE: Zero-Shot Domain Adaptation for Object Detection via Unified Prompt and Representation Enhancement: Xiao Zhang,

Fei Wei,

Yong Wang,

Wenda Zhao,

Feiyi Li,

Xiangxiang Chu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Xiao and Wei, Fei and Wang, Yong and Zhao, Wenda and Li, Feiyi and Chu, Xiangxiang}, title = {UPRE: Zero-Shot Domain Adaptation for Object Detection via Unified Prompt and Representation Enhancement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {508-518} }
Heavy Labels Out! Dataset Distillation with Label Space Lightening: Ruonan Yu,

Songhua Liu,

Zigeng Chen,

Jingwen Ye,

Xinchao Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2025_ICCV, author = {Yu, Ruonan and Liu, Songhua and Chen, Zigeng and Ye, Jingwen and Wang, Xinchao}, title = {Heavy Labels Out! Dataset Distillation with Label Space Lightening}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5017-5026} }
EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds: Lu Chen,

Yizhou Wang,

Shixiang Tang,

Qianhong Ma,

Tong He,

Wanli Ouyang,

Xiaowei Zhou,

Hujun Bao,

Sida Peng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Lu and Wang, Yizhou and Tang, Shixiang and Ma, Qianhong and He, Tong and Ouyang, Wanli and Zhou, Xiaowei and Bao, Hujun and Peng, Sida}, title = {EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6970-6980} }
Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation: Zixin Wang,

Dong Gong,

Sen Wang,

Zi Huang,

Yadan Luo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Zixin and Gong, Dong and Wang, Sen and Huang, Zi and Luo, Yadan}, title = {Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {144-154} }
Global Motion Corresponder for 3D Point-Based Scene Interpolation under Large Motion: Junru Lin,

Chirag Vashist,

Mikaela Angelina Uy,

Colton Stearns,

Xuan Luo,

Leonidas Guibas,

Ke Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2025_ICCV, author = {Lin, Junru and Vashist, Chirag and Uy, Mikaela Angelina and Stearns, Colton and Luo, Xuan and Guibas, Leonidas and Li, Ke}, title = {Global Motion Corresponder for 3D Point-Based Scene Interpolation under Large Motion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7884-7893} }
Revelio: Interpreting and leveraging semantic information in diffusion models: Dahye Kim,

Xavier Thomas,

Deepti Ghadiyaram; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2025_ICCV, author = {Kim, Dahye and Thomas, Xavier and Ghadiyaram, Deepti}, title = {Revelio: Interpreting and leveraging semantic information in diffusion models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4659-4669} }
Spatial-Temporal Aware Visuomotor Diffusion Policy Learning: Zhenyang Liu,

Yikai Wang,

Kuanning Wang,

Longfei Liang,

Xiangyang Xue,

Yanwei Fu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2025_ICCV, author = {Liu, Zhenyang and Wang, Yikai and Wang, Kuanning and Liang, Longfei and Xue, Xiangyang and Fu, Yanwei}, title = {Spatial-Temporal Aware Visuomotor Diffusion Policy Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7122-7131} }
FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases: Shuai Tan,

Bill Gong,

Bin Ji,

Ye Pan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tan_2025_ICCV, author = {Tan, Shuai and Gong, Bill and Ji, Bin and Pan, Ye}, title = {FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {24-36} }
CVPT: Cross Visual Prompt Tuning: Lingyun Huang,

Jianxu Mao,

Junfei Yi,

Ziming Tao,

Yaonan Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Huang_2025_ICCV, author = {Huang, Lingyun and Mao, Jianxu and Yi, Junfei and Tao, Ziming and Wang, Yaonan}, title = {CVPT: Cross Visual Prompt Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {848-858} }
On the Robustness Tradeoff in Fine-Tuning: Kunyang Li,

Jean-Charles Noirot Ferrand,

Ryan Sheatsley,

Blaine Hoak,

Yohan Beugin,

Eric Pauley,

Patrick McDaniel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Kunyang and Ferrand, Jean-Charles Noirot and Sheatsley, Ryan and Hoak, Blaine and Beugin, Yohan and Pauley, Eric and McDaniel, Patrick}, title = {On the Robustness Tradeoff in Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4898-4907} }
VisRL: Intention-Driven Visual Perception via Reinforced Reasoning: Zhangquan Chen,

Xufang Luo,

Dongsheng Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Zhangquan and Luo, Xufang and Li, Dongsheng}, title = {VisRL: Intention-Driven Visual Perception via Reinforced Reasoning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2545-2555} }
Category-Specific Selective Feature Enhancement for Long-Tailed Multi-Label Image Classification: Ruiqi Du,

Xu Tang,

Xiangrong Zhang,

Jingjing Ma; [pdf] [supp]
[bibtex]
@InProceedings{Du_2025_ICCV, author = {Du, Ruiqi and Tang, Xu and Zhang, Xiangrong and Ma, Jingjing}, title = {Category-Specific Selective Feature Enhancement for Long-Tailed Multi-Label Image Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3757-3766} }
Corvid: Improving Multimodal Large Language Models Towards Chain-of-Thought Reasoning: Jingjing Jiang,

Chao Ma,

Xurui Song,

Hanwang Zhang,

Jun Luo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2025_ICCV, author = {Jiang, Jingjing and Ma, Chao and Song, Xurui and Zhang, Hanwang and Luo, Jun}, title = {Corvid: Improving Multimodal Large Language Models Towards Chain-of-Thought Reasoning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3034-3046} }
COSMO: Combination of Selective Memorization for Low-cost Vision-and-Language Navigation: Siqi Zhang,

Yanyuan Qiao,

Qunbo Wang,

Zike Yan,

Qi Wu,

Zhihua Wei,

Jing Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Siqi and Qiao, Yanyuan and Wang, Qunbo and Yan, Zike and Wu, Qi and Wei, Zhihua and Liu, Jing}, title = {COSMO: Combination of Selective Memorization for Low-cost Vision-and-Language Navigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5511-5522} }
STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?: Yun Li,

Yiming Zhang,

Tao Lin,

Xiangrui Liu,

Wenxiao Cai,

Zheng Liu,

Bo Zhao; [pdf]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Yun and Zhang, Yiming and Lin, Tao and Liu, Xiangrui and Cai, Wenxiao and Liu, Zheng and Zhao, Bo}, title = {STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5622-5632} }
CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solvers: Dimitrios Mallis,

Ahmet Serda Karadeniz,

Sebastian Cavada,

Danila Rukhovich,

Niki Foteinopoulou,

Kseniya Cherenkova,

Anis Kacem,

Djamila Aouada; [pdf] [supp]
[bibtex]
@InProceedings{Mallis_2025_ICCV, author = {Mallis, Dimitrios and Karadeniz, Ahmet Serda and Cavada, Sebastian and Rukhovich, Danila and Foteinopoulou, Niki and Cherenkova, Kseniya and Kacem, Anis and Aouada, Djamila}, title = {CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solvers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7284-7294} }
BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation: Yuanhong Yu,

Xingyi He,

Chen Zhao,

Junhao Yu,

Jiaqi Yang,

Ruizhen Hu,

Yujun Shen,

Xing Zhu,

Xiaowei Zhou,

Sida Peng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2025_ICCV, author = {Yu, Yuanhong and He, Xingyi and Zhao, Chen and Yu, Junhao and Yang, Jiaqi and Hu, Ruizhen and Shen, Yujun and Zhu, Xing and Zhou, Xiaowei and Peng, Sida}, title = {BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9374-9384} }
3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding: Tatiana Zemskova,

Dmitry Yudin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zemskova_2025_ICCV, author = {Zemskova, Tatiana and Yudin, Dmitry}, title = {3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8885-8895} }
VGMamba: Attribute-to-Location Clue Reasoning for Quantity-Agnostic 3D Visual Grounding: Yihang Zhu,

Jinhao Zhang,

Yuxuan Wang,

Aming Wu,

Cheng Deng; [pdf]
[bibtex]
@InProceedings{Zhu_2025_ICCV, author = {Zhu, Yihang and Zhang, Jinhao and Wang, Yuxuan and Wu, Aming and Deng, Cheng}, title = {VGMamba: Attribute-to-Location Clue Reasoning for Quantity-Agnostic 3D Visual Grounding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5295-5304} }
Evidential Knowledge Distillation: Liangyu Xiang,

Junyu Gao,

Changsheng Xu; [pdf] [supp]
[bibtex]
@InProceedings{Xiang_2025_ICCV, author = {Xiang, Liangyu and Gao, Junyu and Xu, Changsheng}, title = {Evidential Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2814-2824} }
A Framework for Double-Blind Federated Adaptation of Foundation Models: Nurbek Tastan,

Karthik Nandakumar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tastan_2025_ICCV, author = {Tastan, Nurbek and Nandakumar, Karthik}, title = {A Framework for Double-Blind Federated Adaptation of Foundation Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {923-933} }
Partial Forward Blocking: A Novel Data Pruning Paradigm for Lossless Training Acceleration: Dongyue Wu,

Zilin Guo,

Jialong Zuo,

Nong Sang,

Changxin Gao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2025_ICCV, author = {Wu, Dongyue and Guo, Zilin and Zuo, Jialong and Sang, Nong and Gao, Changxin}, title = {Partial Forward Blocking: A Novel Data Pruning Paradigm for Lossless Training Acceleration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {319-328} }
FedPall: Prototype-based Adversarial and Collaborative Learning for Federated Learning with Feature Drift: Yong Zhang,

Feng Liang,

Guanghu Yuan,

Min Yang,

Chengming Li,

Xiping Hu; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Yong and Liang, Feng and Yuan, Guanghu and Yang, Min and Li, Chengming and Hu, Xiping}, title = {FedPall: Prototype-based Adversarial and Collaborative Learning for Federated Learning with Feature Drift}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3111-3120} }
From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point Supervision: Chuang Yu,

Jinmiao Zhao,

Yunpeng Liu,

Sicheng Zhao,

Yimian Dai,

Xiangyu Yue; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2025_ICCV, author = {Yu, Chuang and Zhao, Jinmiao and Liu, Yunpeng and Zhao, Sicheng and Dai, Yimian and Yue, Xiangyu}, title = {From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point Supervision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2588-2598} }
A Constrained Optimization Approach for Gaussian Splatting from Coarsely-posed Images and Noisy Lidar Point Clouds: Jizong Peng,

Tze Ho Elden Tse,

Kai Xu,

Wenchao Gao,

Angela Yao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Peng_2025_ICCV, author = {Peng, Jizong and Tse, Tze Ho Elden and Xu, Kai and Gao, Wenchao and Yao, Angela}, title = {A Constrained Optimization Approach for Gaussian Splatting from Coarsely-posed Images and Noisy Lidar Point Clouds}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2961-2970} }
BabyVLM: Data-Efficient Pretraining of VLMs Inspired by Infant Learning: Shengao Wang,

Arjun Chandra,

Aoming Liu,

Venkatesh Saligrama,

Boqing Gong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Shengao and Chandra, Arjun and Liu, Aoming and Saligrama, Venkatesh and Gong, Boqing}, title = {BabyVLM: Data-Efficient Pretraining of VLMs Inspired by Infant Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1380-1390} }
Contact-Aware Amodal Completion for Human-Object Interaction via Multi-Regional Inpainting: Seunggeun Chi,

Enna Sachdeva,

Pin-Hao Huang,

Kwonjoon Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chi_2025_ICCV, author = {Chi, Seunggeun and Sachdeva, Enna and Huang, Pin-Hao and Lee, Kwonjoon}, title = {Contact-Aware Amodal Completion for Human-Object Interaction via Multi-Regional Inpainting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9487-9496} }
Ultra-Precision 6DoF Pose Estimation Using 2-D Interpolated Discrete Fourier Transform: Guowei Shi,

Zian Mao,

Peisen Huang; [pdf] [supp]
[bibtex]
@InProceedings{Shi_2025_ICCV, author = {Shi, Guowei and Mao, Zian and Huang, Peisen}, title = {Ultra-Precision 6DoF Pose Estimation Using 2-D Interpolated Discrete Fourier Transform}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5802-5810} }
Uncertainty-Aware Gradient Stabilization for Small Object Detection: Huixin Sun,

Yanjing Li,

Linlin Yang,

Xianbin Cao,

Baochang Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2025_ICCV, author = {Sun, Huixin and Li, Yanjing and Yang, Linlin and Cao, Xianbin and Zhang, Baochang}, title = {Uncertainty-Aware Gradient Stabilization for Small Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8407-8417} }
Radiant Foam: Real-Time Differentiable Ray Tracing: Shrisudhan Govindarajan,

Daniel Rebain,

Kwang Moo Yi,

Andrea Tagliasacchi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Govindarajan_2025_ICCV, author = {Govindarajan, Shrisudhan and Rebain, Daniel and Yi, Kwang Moo and Tagliasacchi, Andrea}, title = {Radiant Foam: Real-Time Differentiable Ray Tracing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4135-4145} }
Attention to the Burstiness in Visual Prompt Tuning!: Yuzhu Wang,

Manni Duan,

Shu Kong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Yuzhu and Duan, Manni and Kong, Shu}, title = {Attention to the Burstiness in Visual Prompt Tuning!}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4253-4263} }
R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization: Yi Yang,

Xiaoxuan He,

Hongkun Pan,

Xiyan Jiang,

Yan Deng,

Xingtao Yang,

Haoyu Lu,

Dacheng Yin,

Fengyun Rao,

Minfeng Zhu,

Bo Zhang,

Wei Chen; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Yi and He, Xiaoxuan and Pan, Hongkun and Jiang, Xiyan and Deng, Yan and Yang, Xingtao and Lu, Haoyu and Yin, Dacheng and Rao, Fengyun and Zhu, Minfeng and Zhang, Bo and Chen, Wei}, title = {R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2376-2385} }
HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding: Jiahe Zhao,

Ruibing Hou,

Zejie Tian,

Hong Chang,

Shiguang Shan; [pdf] [supp]
[bibtex]
@InProceedings{Zhao_2025_ICCV, author = {Zhao, Jiahe and Hou, Ruibing and Tian, Zejie and Chang, Hong and Shan, Shiguang}, title = {HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4317-4327} }
Learnable Logit Adjustment for Imbalanced Semi-Supervised Learning under Class Distribution Mismatch: Hyuck Lee,

Taemin Park,

Heeyoung Kim; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2025_ICCV, author = {Lee, Hyuck and Park, Taemin and Kim, Heeyoung}, title = {Learnable Logit Adjustment for Imbalanced Semi-Supervised Learning under Class Distribution Mismatch}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2664-2674} }
Enhancing Transformers Through Conditioned Embedded Tokens: Hemanth Saratchandran,

Simon Lucey; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Saratchandran_2025_ICCV, author = {Saratchandran, Hemanth and Lucey, Simon}, title = {Enhancing Transformers Through Conditioned Embedded Tokens}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4786-4795} }
CryoFastAR: Fast Cryo-EM Ab initio Reconstruction Made Easy: Jiakai Zhang,

Shouchen Zhou,

Haizhao Dai,

Xinhang Liu,

Peihao Wang,

Zhiwen Fan,

Yuan Pei,

Jingyi Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Jiakai and Zhou, Shouchen and Dai, Haizhao and Liu, Xinhang and Wang, Peihao and Fan, Zhiwen and Pei, Yuan and Yu, Jingyi}, title = {CryoFastAR: Fast Cryo-EM Ab initio Reconstruction Made Easy}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8462-8471} }
Hints of Prompt: Enhancing Visual Representation for Multimodal LLMs in Autonomous Driving: Hao Zhou,

Zhanning Gao,

Zhili Chen,

Maosheng Ye,

Qifeng Chen,

Tongyi Cao,

Honggang Qi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2025_ICCV, author = {Zhou, Hao and Gao, Zhanning and Chen, Zhili and Ye, Maosheng and Chen, Qifeng and Cao, Tongyi and Qi, Honggang}, title = {Hints of Prompt: Enhancing Visual Representation for Multimodal LLMs in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6165-6175} }
RegGS: Unposed Sparse Views Gaussian Splatting with 3DGS Registration: Chong Cheng,

Yu Hu,

Sicheng Yu,

Beizhen Zhao,

Zijian Wang,

Hao Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2025_ICCV, author = {Cheng, Chong and Hu, Yu and Yu, Sicheng and Zhao, Beizhen and Wang, Zijian and Wang, Hao}, title = {RegGS: Unposed Sparse Views Gaussian Splatting with 3DGS Registration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8100-8109} }
RALoc: Enhancing Outdoor LiDAR Localization via Rotation Awareness: Yuyang Yang,

Wen Li,

Sheng Ao,

Qingshan Xu,

Shangshu Yu,

Yu Guo,

Yin Zhou,

Siqi Shen,

Cheng Wang; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Yuyang and Li, Wen and Ao, Sheng and Xu, Qingshan and Yu, Shangshu and Guo, Yu and Zhou, Yin and Shen, Siqi and Wang, Cheng}, title = {RALoc: Enhancing Outdoor LiDAR Localization via Rotation Awareness}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3304-3313} }
LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D Capabilities: Chenming Zhu,

Tai Wang,

Wenwei Zhang,

Jiangmiao Pang,

Xihui Liu; [pdf] [supp]
[bibtex]
@InProceedings{Zhu_2025_ICCV, author = {Zhu, Chenming and Wang, Tai and Zhang, Wenwei and Pang, Jiangmiao and Liu, Xihui}, title = {LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D Capabilities}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4295-4305} }
Understanding Museum Exhibits using Vision-Language Reasoning: Ada-Astrid Balauca,

Sanjana Garai,

Stefan Balauca,

Rasesh Udayakumar Shetty,

Naitik Agrawal,

Dhwanil Subhashbhai Shah,

Yuqian Fu,

Xi Wang,

Kristina Toutanova,

Danda Pani Paudel,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Balauca_2025_ICCV, author = {Balauca, Ada-Astrid and Garai, Sanjana and Balauca, Stefan and Shetty, Rasesh Udayakumar and Agrawal, Naitik and Shah, Dhwanil Subhashbhai and Fu, Yuqian and Wang, Xi and Toutanova, Kristina and Paudel, Danda Pani and Van Gool, Luc}, title = {Understanding Museum Exhibits using Vision-Language Reasoning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2227-2238} }
Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning.: Daniel DeAlcala,

Aythami Morales,

Julian Fierrez,

Gonzalo Mancera,

Ruben Tolosana,

Javier Ortega-Garcia; [pdf] [arXiv]
[bibtex]
@InProceedings{DeAlcala_2025_ICCV, author = {DeAlcala, Daniel and Morales, Aythami and Fierrez, Julian and Mancera, Gonzalo and Tolosana, Ruben and Ortega-Garcia, Javier}, title = {Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning.}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {647-656} }
One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models: Hao Fang,

Jiawei Kong,

Wenbo Yu,

Bin Chen,

Jiawei Li,

Hao Wu,

Shu-Tao Xia,

Ke Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fang_2025_ICCV, author = {Fang, Hao and Kong, Jiawei and Yu, Wenbo and Chen, Bin and Li, Jiawei and Wu, Hao and Xia, Shu-Tao and Xu, Ke}, title = {One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4090-4100} }
Exploring View Consistency for Scene-Adaptive Low-Light Light Field Image Enhancement: Shuo Zhang,

Chen Gao,

Youfang Lin; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Shuo and Gao, Chen and Lin, Youfang}, title = {Exploring View Consistency for Scene-Adaptive Low-Light Light Field Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7340-7349} }
Learning to See Inside Opaque Liquid Containers using Speckle Vibrometry: Matan Kichler,

Shai Bagon,

Mark Sheinin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kichler_2025_ICCV, author = {Kichler, Matan and Bagon, Shai and Sheinin, Mark}, title = {Learning to See Inside Opaque Liquid Containers using Speckle Vibrometry}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9466-9476} }
Debiased Teacher for Day-to-Night Domain Adaptive Object Detection: Yiming Cui,

Liang Li,

Haibing Yin,

Yuhan Gao,

Yaoqi Sun,

Chenggang Yan; [pdf] [supp]
[bibtex]
@InProceedings{Cui_2025_ICCV, author = {Cui, Yiming and Li, Liang and Yin, Haibing and Gao, Yuhan and Sun, Yaoqi and Yan, Chenggang}, title = {Debiased Teacher for Day-to-Night Domain Adaptive Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2577-2587} }
Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting: Yuqi Li,

Chuanguang Yang,

Hansheng Zeng,

Zeyu Dong,

Zhulin An,

Yongjun Xu,

Yingli Tian,

Hao Wu; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Yuqi and Yang, Chuanguang and Zeng, Hansheng and Dong, Zeyu and An, Zhulin and Xu, Yongjun and Tian, Yingli and Wu, Hao}, title = {Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7262-7272} }
Image as an IMU: Estimating Camera Motion from a Single Motion-Blurred Image: Jerred Chen,

Ronald Clark; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Jerred and Clark, Ronald}, title = {Image as an IMU: Estimating Camera Motion from a Single Motion-Blurred Image}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {90-99} }
MemDistill: Distilling LiDAR Knowledge into Memory for Camera-Only 3D Object Detection: Donghyeon Kwon,

Youngseok Yoon,

Hyeongseok Son,

Suha Kwak; [pdf]
[bibtex]
@InProceedings{Kwon_2025_ICCV, author = {Kwon, Donghyeon and Yoon, Youngseok and Son, Hyeongseok and Kwak, Suha}, title = {MemDistill: Distilling LiDAR Knowledge into Memory for Camera-Only 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6828-6838} }
OpenRSD: Towards Open-prompts for Object Detection in Remote Sensing Images: Ziyue Huang,

Yongchao Feng,

Ziqi Liu,

Shuai Yang,

Qingjie Liu,

Yunhong Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2025_ICCV, author = {Huang, Ziyue and Feng, Yongchao and Liu, Ziqi and Yang, Shuai and Liu, Qingjie and Wang, Yunhong}, title = {OpenRSD: Towards Open-prompts for Object Detection in Remote Sensing Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8384-8394} }
FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution: Gene Chou,

Wenqi Xian,

Guandao Yang,

Mohamed Abdelfattah,

Bharath Hariharan,

Noah Snavely,

Ning Yu,

Paul Debevec; [pdf] [arXiv]
[bibtex]
@InProceedings{Chou_2025_ICCV, author = {Chou, Gene and Xian, Wenqi and Yang, Guandao and Abdelfattah, Mohamed and Hariharan, Bharath and Snavely, Noah and Yu, Ning and Debevec, Paul}, title = {FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9638-9648} }
Towards Performance Consistency in Multi-Level Model Collaboration: Qi Li,

Runpeng Yu,

Xinchao Wang; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Qi and Yu, Runpeng and Wang, Xinchao}, title = {Towards Performance Consistency in Multi-Level Model Collaboration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2567-2576} }
Where, What, Why: Towards Explainable Driver Attention Prediction: Yuchen Zhou,

Jiayu Tang,

Xiaoyan Xiao,

Yueyao Lin,

Linkai Liu,

Zipeng Guo,

Hao Fei,

Xiaobo Xia,

Chao Gou; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhou_2025_ICCV, author = {Zhou, Yuchen and Tang, Jiayu and Xiao, Xiaoyan and Lin, Yueyao and Liu, Linkai and Guo, Zipeng and Fei, Hao and Xia, Xiaobo and Gou, Chao}, title = {Where, What, Why: Towards Explainable Driver Attention Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2675-2685} }
Visual Intention Grounding for Egocentric Assistants: Pengzhan Sun,

Junbin Xiao,

Tze Ho Elden Tse,

Yicong Li,

Arjun Akula,

Angela Yao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2025_ICCV, author = {Sun, Pengzhan and Xiao, Junbin and Tse, Tze Ho Elden and Li, Yicong and Akula, Arjun and Yao, Angela}, title = {Visual Intention Grounding for Egocentric Assistants}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2512-2522} }
Analyzing Finetuning Representation Shift for Multimodal LLMs Steering: Pegah Khayatan,

Mustafa Shukor,

Jayneel Parekh,

Arnaud Dapogny,

Matthieu Cord; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Khayatan_2025_ICCV, author = {Khayatan, Pegah and Shukor, Mustafa and Parekh, Jayneel and Dapogny, Arnaud and Cord, Matthieu}, title = {Analyzing Finetuning Representation Shift for Multimodal LLMs Steering}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2206-2216} }
Harnessing Massive Satellite Imagery with Efficient Masked Image Modeling: Fengxiang Wang,

Hongzhen Wang,

Di Wang,

Zonghao Guo,

Zhenyu Zhong,

Long Lan,

Wenjing Yang,

Jing Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Fengxiang and Wang, Hongzhen and Wang, Di and Guo, Zonghao and Zhong, Zhenyu and Lan, Long and Yang, Wenjing and Zhang, Jing}, title = {Harnessing Massive Satellite Imagery with Efficient Masked Image Modeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6935-6947} }
Visual-Oriented Fine-Grained Knowledge Editing for MultiModal Large Language Models: Zhen Zeng,

Leijiang Gu,

Xun Yang,

Zhangling Duan,

Zenglin Shi,

Meng Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zeng_2025_ICCV, author = {Zeng, Zhen and Gu, Leijiang and Yang, Xun and Duan, Zhangling and Shi, Zenglin and Wang, Meng}, title = {Visual-Oriented Fine-Grained Knowledge Editing for MultiModal Large Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2491-2500} }
A Recipe for Generating 3D Worlds from a Single Image: Katja Schwarz,

Denis Rozumny,

Samuel Rota Bulò,

Lorenzo Porzi,

Peter Kontschieder; [pdf] [supp]
[bibtex]
@InProceedings{Schwarz_2025_ICCV, author = {Schwarz, Katja and Rozumny, Denis and Bul\`o, Samuel Rota and Porzi, Lorenzo and Kontschieder, Peter}, title = {A Recipe for Generating 3D Worlds from a Single Image}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3520-3530} }
MVGBench: a Comprehensive Benchmark for Multi-view Generation Models: Xianghui Xie,

Jan Eric Lessen,

Gerard Pons-Moll; [pdf] [supp]
[bibtex]
@InProceedings{Xie_2025_ICCV, author = {Xie, Xianghui and Lessen, Jan Eric and Pons-Moll, Gerard}, title = {MVGBench: a Comprehensive Benchmark for Multi-view Generation Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8207-8218} }
Fewer Denoising Steps or Cheaper Per-Step Inference: Towards Compute-Optimal Diffusion Model Deployment: Zhenbang Du,

Yonggan Fu,

Lifu Wang,

Jiayi Qian,

Xiao Luo,

Yingyan Celine Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Du_2025_ICCV, author = {Du, Zhenbang and Fu, Yonggan and Wang, Lifu and Qian, Jiayi and Luo, Xiao and Lin, Yingyan Celine}, title = {Fewer Denoising Steps or Cheaper Per-Step Inference: Towards Compute-Optimal Diffusion Model Deployment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3001-3010} }
Competitive Distillation: A Simple Learning Strategy for Improving Visual Classification: Daqian Shi,

Xiaolei Diao,

Xu Chen,

Cédric M John; [pdf] [arXiv]
[bibtex]
@InProceedings{Shi_2025_ICCV, author = {Shi, Daqian and Diao, Xiaolei and Chen, Xu and John, C\'edric M}, title = {Competitive Distillation: A Simple Learning Strategy for Improving Visual Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2981-2990} }
AllTracker: Efficient Dense Point Tracking at High Resolution: Adam W. Harley,

Yang You,

Xinglong Sun,

Yang Zheng,

Nikhil Raghuraman,

Yunqi Gu,

Sheldon Liang,

Wen-Hsuan Chu,

Achal Dave,

Suya You,

Rares Ambrus,

Katerina Fragkiadaki,

Leonidas Guibas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Harley_2025_ICCV, author = {Harley, Adam W. and You, Yang and Sun, Xinglong and Zheng, Yang and Raghuraman, Nikhil and Gu, Yunqi and Liang, Sheldon and Chu, Wen-Hsuan and Dave, Achal and You, Suya and Ambrus, Rares and Fragkiadaki, Katerina and Guibas, Leonidas}, title = {AllTracker: Efficient Dense Point Tracking at High Resolution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5253-5262} }
Social Debiasing for Fair Multi-modal LLMs: Harry Cheng,

Yangyang Guo,

Qingpei Guo,

Ming Yang,

Tian Gan,

Weili Guan,

Liqiang Nie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2025_ICCV, author = {Cheng, Harry and Guo, Yangyang and Guo, Qingpei and Yang, Ming and Gan, Tian and Guan, Weili and Nie, Liqiang}, title = {Social Debiasing for Fair Multi-modal LLMs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1740-1750} }
DOGR: Towards Versatile Visual Document Grounding and Referring: Yinan Zhou,

Yuxin Chen,

Haokun Lin,

Yichen Wu,

Shuyu Yang,

Zhongang Qi,

Chen Ma,

Li Zhu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2025_ICCV, author = {Zhou, Yinan and Chen, Yuxin and Lin, Haokun and Wu, Yichen and Yang, Shuyu and Qi, Zhongang and Ma, Chen and Zhu, Li}, title = {DOGR: Towards Versatile Visual Document Grounding and Referring}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3596-3606} }
MixRI: Mixing Features of Reference Images for Novel Object Pose Estimation: Xinhang Liu,

Jiawei Shi,

Zheng Dang,

Yuchao Dai; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2025_ICCV, author = {Liu, Xinhang and Shi, Jiawei and Dang, Zheng and Dai, Yuchao}, title = {MixRI: Mixing Features of Reference Images for Novel Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9024-9035} }
DiffuMatch: Category-Agnostic Spectral Diffusion Priors for Robust Non-rigid Shape Matching: Emery Pierson,

Lei Li,

Angela Dai,

Maks Ovsjanikov; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pierson_2025_ICCV, author = {Pierson, Emery and Li, Lei and Dai, Angela and Ovsjanikov, Maks}, title = {DiffuMatch: Category-Agnostic Spectral Diffusion Priors for Robust Non-rigid Shape Matching}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5745-5756} }
Adversarial Attention Perturbations for Large Object Detection Transformers: Zachary Yahn,

Selim Furkan Tekin,

Fatih Ilhan,

Sihao Hu,

Tiansheng Huang,

Yichang Xu,

Margaret Loper,

Ling Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yahn_2025_ICCV, author = {Yahn, Zachary and Tekin, Selim Furkan and Ilhan, Fatih and Hu, Sihao and Huang, Tiansheng and Xu, Yichang and Loper, Margaret and Liu, Ling}, title = {Adversarial Attention Perturbations for Large Object Detection Transformers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3184-3193} }
Meta-Learning Dynamic Center Distance: Hard Sample Mining for Learning with Noisy Labels: Chenyu Mu,

Yijun Qu,

Jiexi Yan,

Erkun Yang,

Cheng Deng; [pdf] [supp]
[bibtex]
@InProceedings{Mu_2025_ICCV, author = {Mu, Chenyu and Qu, Yijun and Yan, Jiexi and Yang, Erkun and Deng, Cheng}, title = {Meta-Learning Dynamic Center Distance: Hard Sample Mining for Learning with Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {415-425} }
Joint Diffusion Models in Continual Learning: Paweł Skierś,

Kamil Deja; [pdf] [supp]
[bibtex]
@InProceedings{Skiers_2025_ICCV, author = {Skier\'s, Pawe{\l} and Deja, Kamil}, title = {Joint Diffusion Models in Continual Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4380-4390} }
MissRAG: Addressing the Missing Modality Challenge in Multimodal Large Language Models: Vittorio Pipoli,

Alessia Saporita,

Federico Bolelli,

Marcella Cornia,

Lorenzo Baraldi,

Costantino Grana,

Rita Cucchiara,

Elisa Ficarra; [pdf] [supp]
[bibtex]
@InProceedings{Pipoli_2025_ICCV, author = {Pipoli, Vittorio and Saporita, Alessia and Bolelli, Federico and Cornia, Marcella and Baraldi, Lorenzo and Grana, Costantino and Cucchiara, Rita and Ficarra, Elisa}, title = {MissRAG: Addressing the Missing Modality Challenge in Multimodal Large Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3215-3224} }
Test-Time Prompt Tuning for Zero-Shot Depth Completion: Chanhwi Jeong,

Inhwan Bae,

Jin-Hwi Park,

Hae-Gon Jeon; [pdf] [supp]
[bibtex]
@InProceedings{Jeong_2025_ICCV, author = {Jeong, Chanhwi and Bae, Inhwan and Park, Jin-Hwi and Jeon, Hae-Gon}, title = {Test-Time Prompt Tuning for Zero-Shot Depth Completion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9443-9454} }
AstroLoc: Robust Space to Ground Image Localizer: Gabriele Berton,

Alex Stoken,

Carlo Masone; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Berton_2025_ICCV, author = {Berton, Gabriele and Stoken, Alex and Masone, Carlo}, title = {AstroLoc: Robust Space to Ground Image Localizer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5811-5820} }
Chimera: Improving Generalist Model with Domain-Specific Experts: Tianshuo Peng,

Mingsheng Li,

Jiakang Yuan,

Hongbin Zhou,

Renqiu Xia,

Renrui Zhang,

Lei Bai,

Song Mao,

Bin Wang,

Aojun Zhou,

Botian Shi,

Tao Chen,

Bo Zhang,

Xiangyu Yue; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Peng_2025_ICCV, author = {Peng, Tianshuo and Li, Mingsheng and Yuan, Jiakang and Zhou, Hongbin and Xia, Renqiu and Zhang, Renrui and Bai, Lei and Mao, Song and Wang, Bin and Zhou, Aojun and Shi, Botian and Chen, Tao and Zhang, Bo and Yue, Xiangyu}, title = {Chimera: Improving Generalist Model with Domain-Specific Experts}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3011-3022} }
Simultaneous Motion And Noise Estimation with Event Cameras: Shintaro Shiba,

Yoshimitsu Aoki,

Guillermo Gallego; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shiba_2025_ICCV, author = {Shiba, Shintaro and Aoki, Yoshimitsu and Gallego, Guillermo}, title = {Simultaneous Motion And Noise Estimation with Event Cameras}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6959-6969} }
CIARD: Cyclic Iterative Adversarial Robustness Distillation: Liming Lu,

Shuchao Pang,

Xu Zheng,

Xiang Gu,

Anan Du,

Yunhuai Liu,

Yongbin Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2025_ICCV, author = {Lu, Liming and Pang, Shuchao and Zheng, Xu and Gu, Xiang and Du, Anan and Liu, Yunhuai and Zhou, Yongbin}, title = {CIARD: Cyclic Iterative Adversarial Robustness Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {350-359} }
Local Dense Logit Relations for Enhanced Knowledge Distillation: Liuchi Xu,

Kang Liu,

Jinshuai Liu,

Lu Wang,

Lisheng Xu,

Jun Cheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2025_ICCV, author = {Xu, Liuchi and Liu, Kang and Liu, Jinshuai and Wang, Lu and Xu, Lisheng and Cheng, Jun}, title = {Local Dense Logit Relations for Enhanced Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4539-4549} }
Less is More: Empowering GUI Agent with Context-Aware Simplification: Gongwei Chen,

Xurui Zhou,

Rui Shao,

Yibo Lyu,

Kaiwen Zhou,

Shuai Wang,

Wentao Li,

Yinchuan Li,

Zhongang Qi,

Liqiang Nie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Gongwei and Zhou, Xurui and Shao, Rui and Lyu, Yibo and Zhou, Kaiwen and Wang, Shuai and Li, Wentao and Li, Yinchuan and Qi, Zhongang and Nie, Liqiang}, title = {Less is More: Empowering GUI Agent with Context-Aware Simplification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5901-5911} }
Detect Anything 3D in the Wild: Hanxue Zhang,

Haoran Jiang,

Qingsong Yao,

Yanan Sun,

Renrui Zhang,

Hao Zhao,

Hongyang Li,

Hongzi Zhu,

Zetong Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Hanxue and Jiang, Haoran and Yao, Qingsong and Sun, Yanan and Zhang, Renrui and Zhao, Hao and Li, Hongyang and Zhu, Hongzi and Yang, Zetong}, title = {Detect Anything 3D in the Wild}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5048-5059} }
Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training: Yanyun Wang,

Li Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Yanyun and Liu, Li}, title = {Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4691-4700} }
Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians: Quankai Gao,

Iliyan Georgiev,

Tuanfeng Y. Wang,

Krishna Kumar Singh,

Ulrich Neumann,

Jae Shin Yoon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2025_ICCV, author = {Gao, Quankai and Georgiev, Iliyan and Wang, Tuanfeng Y. and Singh, Krishna Kumar and Neumann, Ulrich and Yoon, Jae Shin}, title = {Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9320-9331} }
HFD-Teacher: High-Frequency Depth Distillation from Depth Foundation Models for Enhanced Depth Completion: Zhiyuan Yang,

Anqi Cheng,

Haiyue Zhu,

Tianjiao Li,

Pey Yuen Tao,

Kezhi Mao; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Zhiyuan and Cheng, Anqi and Zhu, Haiyue and Li, Tianjiao and Tao, Pey Yuen and Mao, Kezhi}, title = {HFD-Teacher: High-Frequency Depth Distillation from Depth Foundation Models for Enhanced Depth Completion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8994-9003} }
Looking in the Mirror: A Faithful Counterfactual Explanation Method for Interpreting Deep Image Classification Models: Townim Chowdhury,

Vu Minh Hieu Phan,

Kewen Liao,

Nanyu Dong,

Minh-Son To,

Anton van den Hengel,

Johan W. Verjans,

Zhibin Liao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chowdhury_2025_ICCV, author = {Chowdhury, Townim and Phan, Vu Minh Hieu and Liao, Kewen and Dong, Nanyu and To, Minh-Son and van den Hengel, Anton and Verjans, Johan W. and Liao, Zhibin}, title = {Looking in the Mirror: A Faithful Counterfactual Explanation Method for Interpreting Deep Image Classification Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2239-2249} }
Inference-Time Diffusion Model Distillation: Geon Yeong Park,

Sang Wan Lee,

Jong Chul Ye; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2025_ICCV, author = {Park, Geon Yeong and Lee, Sang Wan and Ye, Jong Chul}, title = {Inference-Time Diffusion Model Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4049-4058} }
Target Bias Is All You Need: Zero-Shot Debiasing of Vision-Language Models with Bias Corpus: Taeuk Jang,

Hoin Jung,

Xiaoqian Wang; [pdf] [supp]
[bibtex]
@InProceedings{Jang_2025_ICCV, author = {Jang, Taeuk and Jung, Hoin and Wang, Xiaoqian}, title = {Target Bias Is All You Need: Zero-Shot Debiasing of Vision-Language Models with Bias Corpus}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1935-1946} }
Mastering Collaborative Multi-modal Data Selection: A Focus on Informativeness, Uniqueness, and Representativeness: Qifan Yu,

Zhebei Shen,

Zhongqi Yue,

Yang Wu,

Bosheng Qin,

Wenqiao Zhang,

Yunfei Li,

Juncheng Li,

Siliang Tang,

Yueting Zhuang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2025_ICCV, author = {Yu, Qifan and Shen, Zhebei and Yue, Zhongqi and Wu, Yang and Qin, Bosheng and Zhang, Wenqiao and Li, Yunfei and Li, Juncheng and Tang, Siliang and Zhuang, Yueting}, title = {Mastering Collaborative Multi-modal Data Selection: A Focus on Informativeness, Uniqueness, and Representativeness}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {155-165} }
XTrack: Multimodal Training Boosts RGB-X Video Object Trackers: Yuedong Tan,

Zongwei Wu,

Yuqian Fu,

Zhuyun Zhou,

Guolei Sun,

Eduard Zamfir,

Chao Ma,

Danda Paudel,

Luc Van Gool,

Radu Timofte; [pdf] [supp]
[bibtex]
@InProceedings{Tan_2025_ICCV, author = {Tan, Yuedong and Wu, Zongwei and Fu, Yuqian and Zhou, Zhuyun and Sun, Guolei and Zamfir, Eduard and Ma, Chao and Paudel, Danda and Van Gool, Luc and Timofte, Radu}, title = {XTrack: Multimodal Training Boosts RGB-X Video Object Trackers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5734-5744} }
ChartPoint: Guiding MLLMs with Grounding Reflection for Chart Reasoning: Zhengzhuo Xu,

SiNan Du,

Yiyan Qi,

Siwen Lu,

Chengjin Xu,

Chun Yuan,

Jian Guo; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2025_ICCV, author = {Xu, Zhengzhuo and Du, SiNan and Qi, Yiyan and Lu, Siwen and Xu, Chengjin and Yuan, Chun and Guo, Jian}, title = {ChartPoint: Guiding MLLMs with Grounding Reflection for Chart Reasoning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {426-436} }
On the Generalization of Representation Uncertainty in Earth Observation: Spyros Kondylatos,

Nikolaos Ioannis Bountos,

Dimitrios Michail,

Xiao Xiang Zhu,

Gustau Camps-Valls,

Ioannis Papoutsis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kondylatos_2025_ICCV, author = {Kondylatos, Spyros and Bountos, Nikolaos Ioannis and Michail, Dimitrios and Zhu, Xiao Xiang and Camps-Valls, Gustau and Papoutsis, Ioannis}, title = {On the Generalization of Representation Uncertainty in Earth Observation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6552-6562} }
Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack: Xingshuo Han,

Xuanye Zhang,

Xiang Lan,

Haozhao Wang,

Shengmin Xu,

Shen Ren,

Jason Zeng,

Ming Wu,

Michael Heinrich,

Tianwei Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Han_2025_ICCV, author = {Han, Xingshuo and Zhang, Xuanye and Lan, Xiang and Wang, Haozhao and Xu, Shengmin and Ren, Shen and Zeng, Jason and Wu, Ming and Heinrich, Michael and Zhang, Tianwei}, title = {Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1580-1589} }
ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling: Jinhyung Park,

Javier Romero,

Shunsuke Saito,

Fabian Prada,

Takaaki Shiratori,

Yichen Xu,

Federica Bogo,

Shoou-I Yu,

Kris Kitani,

Rawal Khirodkar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2025_ICCV, author = {Park, Jinhyung and Romero, Javier and Saito, Shunsuke and Prada, Fabian and Shiratori, Takaaki and Xu, Yichen and Bogo, Federica and Yu, Shoou-I and Kitani, Kris and Khirodkar, Rawal}, title = {ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6508-6518} }
PHATNet: A Physics-guided Haze Transfer Network for Domain-adaptive Real-world Image Dehazing: Fu-Jen Tsai,

Yan-Tsung Peng,

Yen-Yu Lin,

Chia-Wen Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tsai_2025_ICCV, author = {Tsai, Fu-Jen and Peng, Yan-Tsung and Lin, Yen-Yu and Lin, Chia-Wen}, title = {PHATNet: A Physics-guided Haze Transfer Network for Domain-adaptive Real-world Image Dehazing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5591-5600} }
Diagnosing Pretrained Models for Out-of-distribution Detection: Haipeng Xiong,

Kai Xu,

Angela Yao; [pdf] [supp]
[bibtex]
@InProceedings{Xiong_2025_ICCV, author = {Xiong, Haipeng and Xu, Kai and Yao, Angela}, title = {Diagnosing Pretrained Models for Out-of-distribution Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1836-1845} }
Equipping Vision Foundation Model with Mixture of Experts for Out-of-Distribution Detection: Shizhen Zhao,

Jiahui Liu,

Xin Wen,

Haoru Tan,

Xiaojuan Qi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2025_ICCV, author = {Zhao, Shizhen and Liu, Jiahui and Wen, Xin and Tan, Haoru and Qi, Xiaojuan}, title = {Equipping Vision Foundation Model with Mixture of Experts for Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1751-1761} }
BlinkTrack: Feature Tracking over 80 FPS via Events and Images: Yichen Shen,

Yijin Li,

Shuo Chen,

Guanglin Li,

Zhaoyang Huang,

Hujun Bao,

Zhaopeng Cui,

Guofeng Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shen_2025_ICCV, author = {Shen, Yichen and Li, Yijin and Chen, Shuo and Li, Guanglin and Huang, Zhaoyang and Bao, Hujun and Cui, Zhaopeng and Zhang, Guofeng}, title = {BlinkTrack: Feature Tracking over 80 FPS via Events and Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9298-9308} }
CAVIS: Context-Aware Video Instance Segmentation: Seunghun Lee,

Jiwan Seo,

Kiljoon Han,

Minwoo Choi,

Sunghoon Im; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2025_ICCV, author = {Lee, Seunghun and Seo, Jiwan and Han, Kiljoon and Choi, Minwoo and Im, Sunghoon}, title = {CAVIS: Context-Aware Video Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4507-4517} }
AR-VRM: Imitating Human Motions for Visual Robot Manipulation with Analogical Reasoning: Dejie Yang,

Zijing Zhao,

Yang Liu; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Dejie and Zhao, Zijing and Liu, Yang}, title = {AR-VRM: Imitating Human Motions for Visual Robot Manipulation with Analogical Reasoning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6818-6827} }
HccePose(BF): Predicting Front & Back Surfaces to Construct Ultra-Dense 2D-3D Correspondences for Pose Estimation: Yulin Wang,

Mengting Hu,

Hongli Li,

Chen Luo; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Yulin and Hu, Mengting and Li, Hongli and Luo, Chen}, title = {HccePose(BF): Predicting Front \& Back Surfaces to Construct Ultra-Dense 2D-3D Correspondences for Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7166-7175} }
Find Any Part in 3D: Ziqi Ma,

Yisong Yue,

Georgia Gkioxari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2025_ICCV, author = {Ma, Ziqi and Yue, Yisong and Gkioxari, Georgia}, title = {Find Any Part in 3D}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7818-7827} }
MMOne: Representing Multiple Modalities in One Scene: Zhifeng Gu,

Bing Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gu_2025_ICCV, author = {Gu, Zhifeng and Wang, Bing}, title = {MMOne: Representing Multiple Modalities in One Scene}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1088-1098} }
VA-MoE: Variables-Adaptive Mixture of Experts for Incremental Weather Forecasting: Hao Chen,

Han Tao,

Guo Song,

Jie Zhang,

Yonghan Dong,

Yunlong Yu,

Lei Bai; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Hao and Tao, Han and Song, Guo and Zhang, Jie and Dong, Yonghan and Yu, Yunlong and Bai, Lei}, title = {VA-MoE: Variables-Adaptive Mixture of Experts for Incremental Weather Forecasting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7915-7924} }
Embodied Navigation with Auxiliary Task of Action Description Prediction: Haru Kondoh,

Asako Kanezaki; [pdf] [supp]
[bibtex]
@InProceedings{Kondoh_2025_ICCV, author = {Kondoh, Haru and Kanezaki, Asako}, title = {Embodied Navigation with Auxiliary Task of Action Description Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7025-7036} }
Taming the Untamed: Graph-Based Knowledge Retrieval and Reasoning for MLLMs to Conquer the Unknown: Bowen Wang,

Zhouqiang Jiang,

Yasuaki Susumu,

Shotaro Miwa,

Tianwei Chen,

Yuta Nakashima; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Bowen and Jiang, Zhouqiang and Susumu, Yasuaki and Miwa, Shotaro and Chen, Tianwei and Nakashima, Yuta}, title = {Taming the Untamed: Graph-Based Knowledge Retrieval and Reasoning for MLLMs to Conquer the Unknown}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4732-4742} }
Diffusion Curriculum: Synthetic-to-Real Data Curriculum via Image-Guided Diffusion: Yijun Liang,

Shweta Bhardwaj,

Tianyi Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liang_2025_ICCV, author = {Liang, Yijun and Bhardwaj, Shweta and Zhou, Tianyi}, title = {Diffusion Curriculum: Synthetic-to-Real Data Curriculum via Image-Guided Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1697-1707} }
CCL-LGS: Contrastive Codebook Learning for 3D Language Gaussian Splatting: Lei Tian,

Xiaomin Li,

Liqian Ma,

Hao Yin,

Zirui Zheng,

Hefei Huang,

Taiqing Li,

Huchuan Lu,

Xu Jia; [pdf] [supp]
[bibtex]
@InProceedings{Tian_2025_ICCV, author = {Tian, Lei and Li, Xiaomin and Ma, Liqian and Yin, Hao and Zheng, Zirui and Huang, Hefei and Li, Taiqing and Lu, Huchuan and Jia, Xu}, title = {CCL-LGS: Contrastive Codebook Learning for 3D Language Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9855-9864} }
TRACE: Learning 3D Gaussian Physical Dynamics from Multi-view Videos: Jinxi Li,

Ziyang Song,

Bo Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Jinxi and Song, Ziyang and Yang, Bo}, title = {TRACE: Learning 3D Gaussian Physical Dynamics from Multi-view Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8820-8829} }
EA-Vit: Efficient Adaptation for Elastic Vision Transformer: Chen Zhu,

Wangbo Zhao,

Huiwen Zhang,

Yuhao Zhou,

Weidong Tang,

Shuo Wang,

Zhihang Yuan,

Yuzhang Shang,

Xiaojiang Peng,

Kai Wang,

Dawei Yang; [pdf] [supp]
[bibtex]
@InProceedings{Zhu_2025_ICCV, author = {Zhu, Chen and Zhao, Wangbo and Zhang, Huiwen and Zhou, Yuhao and Tang, Weidong and Wang, Shuo and Yuan, Zhihang and Shang, Yuzhang and Peng, Xiaojiang and Wang, Kai and Yang, Dawei}, title = {EA-Vit: Efficient Adaptation for Elastic Vision Transformer}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1038-1047} }
Aether: Geometric-Aware Unified World Modeling: Haoyi Zhu,

Yifan Wang,

Jianjun Zhou,

Wenzheng Chang,

Yang Zhou,

Zizun Li,

Junyi Chen,

Chunhua Shen,

Jiangmiao Pang,

Tong He; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2025_ICCV, author = {Zhu, Haoyi and Wang, Yifan and Zhou, Jianjun and Chang, Wenzheng and Zhou, Yang and Li, Zizun and Chen, Junyi and Shen, Chunhua and Pang, Jiangmiao and He, Tong}, title = {Aether: Geometric-Aware Unified World Modeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8535-8546} }
Membership Inference Attacks with False Discovery Rate Control: Chenxu Zhao,

Wei Qian,

Aobo Chen,

Mengdi Huai; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhao_2025_ICCV, author = {Zhao, Chenxu and Qian, Wei and Chen, Aobo and Huai, Mengdi}, title = {Membership Inference Attacks with False Discovery Rate Control}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1216-1227} }
Adversarial Training for Probabilistic Robustness: Yi Zhang,

Yuhang Chen,

Zhen Chen,

Wenjie Ruan,

Xiaowei Huang,

Siddartha Khastgir,

Xingyu Zhao; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Yi and Chen, Yuhang and Chen, Zhen and Ruan, Wenjie and Huang, Xiaowei and Khastgir, Siddartha and Zhao, Xingyu}, title = {Adversarial Training for Probabilistic Robustness}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1675-1685} }
MUNBa: Machine Unlearning via Nash Bargaining: Jing Wu,

Mehrtash Harandi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2025_ICCV, author = {Wu, Jing and Harandi, Mehrtash}, title = {MUNBa: Machine Unlearning via Nash Bargaining}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4754-4765} }
VolumetricSMPL: A Neural Volumetric Body Model for Efficient Interactions, Contacts, and Collisions: Marko Mihajlovic,

Siwei Zhang,

Gen Li,

Kaifeng Zhao,

Lea Muller,

Siyu Tang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mihajlovic_2025_ICCV, author = {Mihajlovic, Marko and Zhang, Siwei and Li, Gen and Zhao, Kaifeng and Muller, Lea and Tang, Siyu}, title = {VolumetricSMPL: A Neural Volumetric Body Model for Efficient Interactions, Contacts, and Collisions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5060-5070} }
Passing the Driving Knowledge Test: Maolin Wei,

Wanzhou Liu,

Eshed Ohn-Bar; [pdf] [arXiv]
[bibtex]
@InProceedings{Wei_2025_ICCV, author = {Wei, Maolin and Liu, Wanzhou and Ohn-Bar, Eshed}, title = {Passing the Driving Knowledge Test}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8395-8406} }
Joint Asymmetric Loss for Learning with Noisy Labels: Jialiang Wang,

Xianming Liu,

Xiong Zhou,

Gangfeng Hu,

Deming Zhai,

Junjun Jiang,

Xiangyang Ji; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Jialiang and Liu, Xianming and Zhou, Xiong and Hu, Gangfeng and Zhai, Deming and Jiang, Junjun and Ji, Xiangyang}, title = {Joint Asymmetric Loss for Learning with Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1947-1956} }
Uncalibrated Structure from Motion on a Sphere: Jonathan Ventura,

Viktor Larsson,

Fredrik Kahl; [pdf] [supp]
[bibtex]
@InProceedings{Ventura_2025_ICCV, author = {Ventura, Jonathan and Larsson, Viktor and Kahl, Fredrik}, title = {Uncalibrated Structure from Motion on a Sphere}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {69-78} }
Online Dense Point Tracking with Streaming Memory: Qiaole Dong,

Yanwei Fu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dong_2025_ICCV, author = {Dong, Qiaole and Fu, Yanwei}, title = {Online Dense Point Tracking with Streaming Memory}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8710-8720} }
STEP-DETR: Advancing DETR-based Semi-Supervised Object Detection with Super Teacher and Pseudo-Label Guided Text Queries: Tahira Shehzadi,

Khurram Azeem Hashmi,

Shalini Sarode,

Didier Stricker,

Muhammad Zeshan Afzal; [pdf] [supp]
[bibtex]
@InProceedings{Shehzadi_2025_ICCV, author = {Shehzadi, Tahira and Hashmi, Khurram Azeem and Sarode, Shalini and Stricker, Didier and Afzal, Muhammad Zeshan}, title = {STEP-DETR: Advancing DETR-based Semi-Supervised Object Detection with Super Teacher and Pseudo-Label Guided Text Queries}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3069-3079} }
Met2Net: A Decoupled Two-Stage Spatio-Temporal Forecasting Model for Complex Meteorological Systems: Shaohan Li,

Hao Yang,

Min Chen,

Xiaolin Qin; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Shaohan and Yang, Hao and Chen, Min and Qin, Xiaolin}, title = {Met2Net: A Decoupled Two-Stage Spatio-Temporal Forecasting Model for Complex Meteorological Systems}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5458-5468} }
egoPPG: Heart Rate Estimation from Eye-Tracking Cameras in Egocentric Systems to Benefit Downstream Vision Tasks: Björn Braun,

Rayan Armani,

Manuel Meier,

Max Moebus,

Christian Holz; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Braun_2025_ICCV, author = {Braun, Bj\"orn and Armani, Rayan and Meier, Manuel and Moebus, Max and Holz, Christian}, title = {egoPPG: Heart Rate Estimation from Eye-Tracking Cameras in Egocentric Systems to Benefit Downstream Vision Tasks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5579-5590} }
Beyond Pixel Uncertainty: Bounding the OoD Objects in Road Scenes: Huachao Zhu,

Zelong Liu,

Zhichao Sun,

Yuda Zou,

Gui-Song Xia,

Yongchao Xu; [pdf]
[bibtex]
@InProceedings{Zhu_2025_ICCV, author = {Zhu, Huachao and Liu, Zelong and Sun, Zhichao and Zou, Yuda and Xia, Gui-Song and Xu, Yongchao}, title = {Beyond Pixel Uncertainty: Bounding the OoD Objects in Road Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8472-8481} }
Learning to See in the Extremely Dark: Hai Jiang,

Binhao Guan,

Zhen Liu,

Xiaohong Liu,

Jian Yu,

Zheng Liu,

Songchen Han,

Shuaicheng Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2025_ICCV, author = {Jiang, Hai and Guan, Binhao and Liu, Zhen and Liu, Xiaohong and Yu, Jian and Liu, Zheng and Han, Songchen and Liu, Shuaicheng}, title = {Learning to See in the Extremely Dark}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7676-7685} }
Scaling Laws for Native Multimodal Models: Mustafa Shukor,

Enrico Fini,

Victor Guilherme Turrisi da Costa,

Matthieu Cord,

Joshua Susskind,

Alaaeldin El-Nouby; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shukor_2025_ICCV, author = {Shukor, Mustafa and Fini, Enrico and da Costa, Victor Guilherme Turrisi and Cord, Matthieu and Susskind, Joshua and El-Nouby, Alaaeldin}, title = {Scaling Laws for Native Multimodal Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {12-23} }
Not All Frame Features Are Equal: Video-to-4D Generation via Decoupling Dynamic-Static Features: Liying Yang,

Chen Liu,

Zhenwei Zhu,

Ajian Liu,

Hui Ma,

Jian Nong,

Yanyan Liang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Liying and Liu, Chen and Zhu, Zhenwei and Liu, Ajian and Ma, Hui and Nong, Jian and Liang, Yanyan}, title = {Not All Frame Features Are Equal: Video-to-4D Generation via Decoupling Dynamic-Static Features}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7494-7504} }
FedDifRC: Unlocking the Potential of Text-to-Image Diffusion Models in Heterogeneous Federated Learning: Huan Wang,

Haoran Li,

Huaming Chen,

Jun Yan,

Jiahua Shi,

Jun Shen; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Huan and Li, Haoran and Chen, Huaming and Yan, Jun and Shi, Jiahua and Shen, Jun}, title = {FedDifRC: Unlocking the Potential of Text-to-Image Diffusion Models in Heterogeneous Federated Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3726-3736} }
MonoMobility: Zero-Shot 3D Mobility Analysis from Monocular Videos: Hongyi Zhou,

Yulan Guo,

Xiaogang Wang,

Kai Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2025_ICCV, author = {Zhou, Hongyi and Guo, Yulan and Wang, Xiaogang and Xu, Kai}, title = {MonoMobility: Zero-Shot 3D Mobility Analysis from Monocular Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8800-8809} }
Prior-aware Dynamic Temporal Modeling Framework for Sequential 3D Hand Pose Estimation: Pengfei Ren,

Jingyu Wang,

Haifeng Sun,

Qi Qi,

Xingyu Liu,

Menghao Zhang,

Lei Zhang,

Jing Wang,

Jianxin Liao; [pdf] [supp]
[bibtex]
@InProceedings{Ren_2025_ICCV, author = {Ren, Pengfei and Wang, Jingyu and Sun, Haifeng and Qi, Qi and Liu, Xingyu and Zhang, Menghao and Zhang, Lei and Wang, Jing and Liao, Jianxin}, title = {Prior-aware Dynamic Temporal Modeling Framework for Sequential 3D Hand Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6476-6487} }
Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery: Xiao Liu,

Nan Pu,

Haiyang Zheng,

Wenjing Li,

Nicu Sebe,

Zhun Zhong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2025_ICCV, author = {Liu, Xiao and Pu, Nan and Zheng, Haiyang and Li, Wenjing and Sebe, Nicu and Zhong, Zhun}, title = {Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1078-1087} }
Visual-RFT: Visual Reinforcement Fine-Tuning: Ziyu Liu,

Zeyi Sun,

Yuhang Zang,

Xiaoyi Dong,

Yuhang Cao,

Haodong Duan,

Dahua Lin,

Jiaqi Wang; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2025_ICCV, author = {Liu, Ziyu and Sun, Zeyi and Zang, Yuhang and Dong, Xiaoyi and Cao, Yuhang and Duan, Haodong and Lin, Dahua and Wang, Jiaqi}, title = {Visual-RFT: Visual Reinforcement Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2034-2044} }
DISTIL: Data-Free Inversion of Suspicious Trojan Inputs via Latent Diffusion: Hossein Mirzaei,

Zeinab Taghavi,

Sepehr Rezaee,

Masoud Hadi,

Moein Madadi,

Mackenzie W. Mathis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mirzaei_2025_ICCV, author = {Mirzaei, Hossein and Taghavi, Zeinab and Rezaee, Sepehr and Hadi, Masoud and Madadi, Moein and Mathis, Mackenzie W.}, title = {DISTIL: Data-Free Inversion of Suspicious Trojan Inputs via Latent Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3194-3205} }
Dynamic Reconstruction of Hand-Object Interaction with Distributed Force-aware Contact Representation: Zhenjun Yu,

Wenqiang Xu,

Pengfei Xie,

Yutong Li,

Brian W. Anthony,

Zhuorui Zhang,

Cewu Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2025_ICCV, author = {Yu, Zhenjun and Xu, Wenqiang and Xie, Pengfei and Li, Yutong and Anthony, Brian W. and Zhang, Zhuorui and Lu, Cewu}, title = {Dynamic Reconstruction of Hand-Object Interaction with Distributed Force-aware Contact Representation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8590-8599} }
Epipolar Consistent Attention Aggregation Network for Unsupervised Light Field Disparity Estimation: Chen Gao,

Shuo Zhang,

Youfang Lin; [pdf] [supp]
[bibtex]
@InProceedings{Gao_2025_ICCV, author = {Gao, Chen and Zhang, Shuo and Lin, Youfang}, title = {Epipolar Consistent Attention Aggregation Network for Unsupervised Light Field Disparity Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6488-6497} }
LLaVA-KD: A Framework of Distilling Multimodal Large Language Models: Yuxuan Cai,

Jiangning Zhang,

Haoyang He,

Xinwei He,

Ao Tong,

Zhenye Gan,

Chengjie Wang,

Zhucun Xue,

Yong Liu,

Xiang Bai; [pdf] [supp]
[bibtex]
@InProceedings{Cai_2025_ICCV, author = {Cai, Yuxuan and Zhang, Jiangning and He, Haoyang and He, Xinwei and Tong, Ao and Gan, Zhenye and Wang, Chengjie and Xue, Zhucun and Liu, Yong and Bai, Xiang}, title = {LLaVA-KD: A Framework of Distilling Multimodal Large Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {239-249} }
CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting: Siyu Jiao,

Haoye Dong,

Yuyang Yin,

Zequn Jie,

Yinlong Qian,

Yao Zhao,

Humphrey Shi,

Yunchao Wei; [pdf] [supp]
[bibtex]
@InProceedings{Jiao_2025_ICCV, author = {Jiao, Siyu and Dong, Haoye and Yin, Yuyang and Jie, Zequn and Qian, Yinlong and Zhao, Yao and Shi, Humphrey and Wei, Yunchao}, title = {CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4670-4680} }
TAPNext: Tracking Any Point (TAP) as Next Token Prediction: Artem Zholus,

Carl Doersch,

Yi Yang,

Skanda Koppula,

Viorica Patraucean,

Xu Owen He,

Ignacio Rocco,

Mehdi S. M. Sajjadi,

Sarath Chandar,

Ross Goroshin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zholus_2025_ICCV, author = {Zholus, Artem and Doersch, Carl and Yang, Yi and Koppula, Skanda and Patraucean, Viorica and He, Xu Owen and Rocco, Ignacio and Sajjadi, Mehdi S. M. and Chandar, Sarath and Goroshin, Ross}, title = {TAPNext: Tracking Any Point (TAP) as Next Token Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9693-9703} }
Learnable Feature Patches and Vectors for Boosting Low-light Image Enhancement without External Knowledge: Xiaogang Xu,

Jiafei Wu,

Qingsen Yan,

Jiequan Cui,

Richang Hong,

Bei Yu; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2025_ICCV, author = {Xu, Xiaogang and Wu, Jiafei and Yan, Qingsen and Cui, Jiequan and Hong, Richang and Yu, Bei}, title = {Learnable Feature Patches and Vectors for Boosting Low-light Image Enhancement without External Knowledge}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7761-7770} }
AnnofreeOD: Detecting All Classes at Low Frame Rates Without Human Annotations: Boyi Sun,

Yuhang Liu,

Houxin He,

Yonglin Tian,

Fei-Yue Wang; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2025_ICCV, author = {Sun, Boyi and Liu, Yuhang and He, Houxin and Tian, Yonglin and Wang, Fei-Yue}, title = {AnnofreeOD: Detecting All Classes at Low Frame Rates Without Human Annotations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5315-5325} }
PanSt3R: Multi-view Consistent Panoptic Segmentation: Lojze Zust,

Yohann Cabon,

Juliette Marrie,

Leonid Antsfeld,

Boris Chidlovskii,

Jerome Revaud,

Gabriela Csurka; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zust_2025_ICCV, author = {Zust, Lojze and Cabon, Yohann and Marrie, Juliette and Antsfeld, Leonid and Chidlovskii, Boris and Revaud, Jerome and Csurka, Gabriela}, title = {PanSt3R: Multi-view Consistent Panoptic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5856-5866} }
CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generation: Jianyu Wu,

Yizhou Wang,

Xiangyu Yue,

Xinzhu Ma,

Jinyang Guo,

Dongzhan Zhou,

Wanli Ouyang,

Shixiang Tang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2025_ICCV, author = {Wu, Jianyu and Wang, Yizhou and Yue, Xiangyu and Ma, Xinzhu and Guo, Jinyang and Zhou, Dongzhan and Ouyang, Wanli and Tang, Shixiang}, title = {CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7014-7024} }
Augmenting Moment Retrieval: Zero-Dependency Two-Stage Learning: Zhengxuan Wei,

Jiajin Tang,

Sibei Yang; [pdf] [supp]
[bibtex]
@InProceedings{Wei_2025_ICCV, author = {Wei, Zhengxuan and Tang, Jiajin and Yang, Sibei}, title = {Augmenting Moment Retrieval: Zero-Dependency Two-Stage Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3401-3412} }
Oasis: One Image is All You Need for Multimodal Instruction Data Synthesis: Letian Zhang,

Quan Cui,

Bingchen Zhao,

Cheng Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Letian and Cui, Quan and Zhao, Bingchen and Yang, Cheng}, title = {Oasis: One Image is All You Need for Multimodal Instruction Data Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3542-3551} }
GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors: Tian-Xing Xu,

Xiangjun Gao,

Wenbo Hu,

Xiaoyu Li,

Song-Hai Zhang,

Ying Shan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2025_ICCV, author = {Xu, Tian-Xing and Gao, Xiangjun and Hu, Wenbo and Li, Xiaoyu and Zhang, Song-Hai and Shan, Ying}, title = {GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6632-6644} }
SpatialTrackerV2: Advancing 3D Point Tracking with Explicit Camera Motion: Yuxi Xiao,

Jianyuan Wang,

Nan Xue,

Nikita Karaev,

Yuri Makarov,

Bingyi Kang,

Xing Zhu,

Hujun Bao,

Yujun Shen,

Xiaowei Zhou; [pdf] [supp]
[bibtex]
@InProceedings{Xiao_2025_ICCV, author = {Xiao, Yuxi and Wang, Jianyuan and Xue, Nan and Karaev, Nikita and Makarov, Yuri and Kang, Bingyi and Zhu, Xing and Bao, Hujun and Shen, Yujun and Zhou, Xiaowei}, title = {SpatialTrackerV2: Advancing 3D Point Tracking with Explicit Camera Motion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6726-6737} }
monoVLN: Bridging the Observation Gap between Monocular and Panoramic Vision and Language Navigation: Renjie Lu,

Yu Zhou,

Hao Cheng,

Jingke Meng,

Wei-Shi Zheng; [pdf] [supp]
[bibtex]
@InProceedings{Lu_2025_ICCV, author = {Lu, Renjie and Zhou, Yu and Cheng, Hao and Meng, Jingke and Zheng, Wei-Shi}, title = {monoVLN: Bridging the Observation Gap between Monocular and Panoramic Vision and Language Navigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9477-9486} }
Know "No" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP: Junsung Park,

Jungbeom Lee,

Jongyoon Song,

Sangwon Yu,

Dahuin Jung,

Sungroh Yoon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2025_ICCV, author = {Park, Junsung and Lee, Jungbeom and Song, Jongyoon and Yu, Sangwon and Jung, Dahuin and Yoon, Sungroh}, title = {Know ''No'' Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2825-2835} }
Gaze-Language Alignment for Zero-Shot Prediction of Visual Search Targets from Human Gaze Scanpaths: Sounak Mondal,

Naveen Sendhilnathan,

Ting Zhang,

Yue Liu,

Michael Proulx,

Michael Louis Iuzzolino,

Chuan Qin,

Tanya R. Jonker; [pdf] [supp]
[bibtex]
@InProceedings{Mondal_2025_ICCV, author = {Mondal, Sounak and Sendhilnathan, Naveen and Zhang, Ting and Liu, Yue and Proulx, Michael and Iuzzolino, Michael Louis and Qin, Chuan and Jonker, Tanya R.}, title = {Gaze-Language Alignment for Zero-Shot Prediction of Visual Search Targets from Human Gaze Scanpaths}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2738-2749} }
ReCoT: Reflective Self-Correction Training for Mitigating Confirmation Bias in Large Vision-Language Models: Mengxue Qu,

Yibo Hu,

Kunyang Han,

Yunchao Wei,

Yao Zhao; [pdf] [supp]
[bibtex]
@InProceedings{Qu_2025_ICCV, author = {Qu, Mengxue and Hu, Yibo and Han, Kunyang and Wei, Yunchao and Zhao, Yao}, title = {ReCoT: Reflective Self-Correction Training for Mitigating Confirmation Bias in Large Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9147-9157} }
From Easy to Hard: The MIR Benchmark for Progressive Interleaved Multi-Image Reasoning: Hang Du,

Jiayang Zhang,

Guoshun Nan,

Wendi Deng,

Zhenyan Chen,

Chenyang Zhang,

Wang Xiao,

Shan Huang,

Yuqi Pan,

Tao Qi,

Sicong Leng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Du_2025_ICCV, author = {Du, Hang and Zhang, Jiayang and Nan, Guoshun and Deng, Wendi and Chen, Zhenyan and Zhang, Chenyang and Xiao, Wang and Huang, Shan and Pan, Yuqi and Qi, Tao and Leng, Sicong}, title = {From Easy to Hard: The MIR Benchmark for Progressive Interleaved Multi-Image Reasoning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {859-869} }
StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data: Yixu Wang,

Yan Teng,

Yingchun Wang,

Xingjun Ma; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Yixu and Teng, Yan and Wang, Yingchun and Ma, Xingjun}, title = {StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {263-272} }
Removing Out-of-Focus Reflective Flares via Color Alignment: Fengbo Lan,

Chang Wen Chen; [pdf]
[bibtex]
@InProceedings{Lan_2025_ICCV, author = {Lan, Fengbo and Chen, Chang Wen}, title = {Removing Out-of-Focus Reflective Flares via Color Alignment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9770-9779} }
MAVias: Mitigate any Visual Bias: Ioannis Sarridis,

Christos Koutlis,

Symeon Papadopoulos,

Christos Diou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sarridis_2025_ICCV, author = {Sarridis, Ioannis and Koutlis, Christos and Papadopoulos, Symeon and Diou, Christos}, title = {MAVias: Mitigate any Visual Bias}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1271-1281} }
Contrastive Flow Matching: George Stoica,

Vivek Ramanujan,

Xiang Fan,

Ali Farhadi,

Ranjay Krishna,

Judy Hoffman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Stoica_2025_ICCV, author = {Stoica, George and Ramanujan, Vivek and Fan, Xiang and Farhadi, Ali and Krishna, Ranjay and Hoffman, Judy}, title = {Contrastive Flow Matching}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1185-1194} }
SemiVisBooster: Boosting Semi-Supervised Learning for Fine-Grained Classification through Pseudo-Label Semantic Guidance: Wenjin Zhang,

Xinyu Li,

Chenyang Gao,

Ivan Marsic; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Wenjin and Li, Xinyu and Gao, Chenyang and Marsic, Ivan}, title = {SemiVisBooster: Boosting Semi-Supervised Learning for Fine-Grained Classification through Pseudo-Label Semantic Guidance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1195-1204} }
Backdooring Self-Supervised Contrastive Learning by Noisy Alignment: Tuo Chen,

Jie Gui,

Minjing Dong,

Ju Jia,

Lanting Fang,

Jian Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Tuo and Gui, Jie and Dong, Minjing and Jia, Ju and Fang, Lanting and Liu, Jian}, title = {Backdooring Self-Supervised Contrastive Learning by Noisy Alignment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3684-3693} }
MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips: Shibo Wang,

Haonan He,

Maria Parelli,

Christoph Gebhardt,

Zicong Fan,

Jie Song; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Shibo and He, Haonan and Parelli, Maria and Gebhardt, Christoph and Fan, Zicong and Song, Jie}, title = {MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5957-5968} }
Trial-Oriented Visual Rearrangement: Yuyi Liu,

Xinhang Song,

Tianliang Qi,

Shuqiang Jiang; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2025_ICCV, author = {Liu, Yuyi and Song, Xinhang and Qi, Tianliang and Jiang, Shuqiang}, title = {Trial-Oriented Visual Rearrangement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8022-8031} }
FusionPhys: A Flexible Framework for Fusing Complementary Sensing Modalities in Remote Physiological Measurement: Chenhang Ying,

Huiyu Yang,

Jieyi Ge,

Zhaodong Sun,

Xu Cheng,

Kui Ren,

Xiaobai Li; [pdf]
[bibtex]
@InProceedings{Ying_2025_ICCV, author = {Ying, Chenhang and Yang, Huiyu and Ge, Jieyi and Sun, Zhaodong and Cheng, Xu and Ren, Kui and Li, Xiaobai}, title = {FusionPhys: A Flexible Framework for Fusing Complementary Sensing Modalities in Remote Physiological Measurement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9363-9373} }
AVAM: a Universal Training-free Adaptive Visual Anchoring Embedded into Multimodal Large Language Model for Multi-image Question Answering: Kang Zeng,

Guojin Zhong,

Jintao Cheng,

Jin Yuan,

Zhiyong Li; [pdf] [supp]
[bibtex]
@InProceedings{Zeng_2025_ICCV, author = {Zeng, Kang and Zhong, Guojin and Cheng, Jintao and Yuan, Jin and Li, Zhiyong}, title = {AVAM: a Universal Training-free Adaptive Visual Anchoring Embedded into Multimodal Large Language Model for Multi-image Question Answering}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2292-2302} }
LIRA: Reasoning Reconstruction via Multimodal Large Language Models: Zhen Zhou,

Tong Wang,

Yunkai Ma,

Xiao Tan,

Fengshui Jing; [pdf] [supp]
[bibtex]
@InProceedings{Zhou_2025_ICCV, author = {Zhou, Zhen and Wang, Tong and Ma, Yunkai and Tan, Xiao and Jing, Fengshui}, title = {LIRA: Reasoning Reconstruction via Multimodal Large Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1762-1772} }
Generate, Transduct, Adapt: Iterative Transduction with VLMs: Oindrila Saha,

Logan Lawrence,

Grant Van Horn,

Subhransu Maji; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Saha_2025_ICCV, author = {Saha, Oindrila and Lawrence, Logan and Van Horn, Grant and Maji, Subhransu}, title = {Generate, Transduct, Adapt: Iterative Transduction with VLMs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1369-1379} }
Test-Time Retrieval-Augmented Adaptation for Vision-Language Models: Xinqi Fan,

Xueli Chen,

Luoxiao Yang,

Chuin Hong Yap,

Rizwan Qureshi,

Qi Dou,

Moi Hoon Yap,

Mubarak Shah; [pdf] [supp]
[bibtex]
@InProceedings{Fan_2025_ICCV, author = {Fan, Xinqi and Chen, Xueli and Yang, Luoxiao and Yap, Chuin Hong and Qureshi, Rizwan and Dou, Qi and Yap, Moi Hoon and Shah, Mubarak}, title = {Test-Time Retrieval-Augmented Adaptation for Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8810-8819} }
Causal Disentanglement and Cross-Modal Alignment for Enhanced Few-Shot Learning: Tianjiao Jiang,

Zhen Zhang,

Yuhang Liu,

Javen Qinfeng Shi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2025_ICCV, author = {Jiang, Tianjiao and Zhang, Zhen and Liu, Yuhang and Shi, Javen Qinfeng}, title = {Causal Disentanglement and Cross-Modal Alignment for Enhanced Few-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {890-900} }
Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimation: Hongyu Wen,

Yiming Zuo,

Venkat Subramanian,

Patrick Chen,

Jia Deng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wen_2025_ICCV, author = {Wen, Hongyu and Zuo, Yiming and Subramanian, Venkat and Chen, Patrick and Deng, Jia}, title = {Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6715-6725} }
NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments: Xuan Yao,

Junyu Gao,

Changsheng Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yao_2025_ICCV, author = {Yao, Xuan and Gao, Junyu and Xu, Changsheng}, title = {NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5536-5546} }
Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion: Shengyuan Zhang,

An Zhao,

Ling Yang,

Zejian Li,

Chenye Meng,

Haoran Xu,

Tianrun Chen,

AnYang Wei,

Perry Pengyun Gu,

Lingyun Sun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Shengyuan and Zhao, An and Yang, Ling and Li, Zejian and Meng, Chenye and Xu, Haoran and Chen, Tianrun and Wei, AnYang and Gu, Perry Pengyun and Sun, Lingyun}, title = {Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5007-5016} }
Self-supervised Learning of Hybrid Part-aware 3D Representations of 2D Gaussians and Superquadrics: Zhirui Gao,

Renjiao Yi,

Yuhang Huang,

Wei Chen,

Chenyang Zhu,

Kai Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2025_ICCV, author = {Gao, Zhirui and Yi, Renjiao and Huang, Yuhang and Chen, Wei and Zhu, Chenyang and Xu, Kai}, title = {Self-supervised Learning of Hybrid Part-aware 3D Representations of 2D Gaussians and Superquadrics}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9649-9659} }
AutoComPose: Automatic Generation of Pose Transition Descriptions for Composed Pose Retrieval Using Multimodal LLMs: Yi-Ting Shen,

Sungmin Eum,

Doheon Lee,

Rohit Shete,

Chiao-Yi Wang,

Heesung Kwon,

Shuvra S. Bhattacharyya; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shen_2025_ICCV, author = {Shen, Yi-Ting and Eum, Sungmin and Lee, Doheon and Shete, Rohit and Wang, Chiao-Yi and Kwon, Heesung and Bhattacharyya, Shuvra S.}, title = {AutoComPose: Automatic Generation of Pose Transition Descriptions for Composed Pose Retrieval Using Multimodal LLMs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7409-7418} }
PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos: Hanxiao Jiang,

Hao-Yu Hsu,

Kaifeng Zhang,

Hsin-Ni Yu,

Shenlong Wang,

Yunzhu Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Jiang_2025_ICCV, author = {Jiang, Hanxiao and Hsu, Hao-Yu and Zhang, Kaifeng and Yu, Hsin-Ni and Wang, Shenlong and Li, Yunzhu}, title = {PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7219-7230} }
RainbowPrompt: Diversity-Enhanced Prompt-Evolving for Continual Learning: Kiseong Hong,

Gyeong-hyeon Kim,

Eunwoo Kim; [pdf] [arXiv]
[bibtex]
@InProceedings{Hong_2025_ICCV, author = {Hong, Kiseong and Kim, Gyeong-hyeon and Kim, Eunwoo}, title = {RainbowPrompt: Diversity-Enhanced Prompt-Evolving for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1130-1140} }
GM-MoE: Low-Light Enhancement with Gated-Mechanism Mixture-of-Experts: Minwen Liao,

Haobo Dong,

Xinyi Wang,

Kurban Ubul,

Yihua Shao,

Ziyang Yan; [pdf] [supp]
[bibtex]
@InProceedings{Liao_2025_ICCV, author = {Liao, Minwen and Dong, Haobo and Wang, Xinyi and Ubul, Kurban and Shao, Yihua and Yan, Ziyang}, title = {GM-MoE: Low-Light Enhancement with Gated-Mechanism Mixture-of-Experts}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8766-8776} }
Beyond Low-Rank Tuning: Model Prior-Guided Rank Allocation for Effective Transfer in Low-Data and Large-Gap Regimes.: Chuyan Zhang,

Kefan Wang,

Yun Gu; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Chuyan and Wang, Kefan and Gu, Yun}, title = {Beyond Low-Rank Tuning: Model Prior-Guided Rank Allocation for Effective Transfer in Low-Data and Large-Gap Regimes.}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3337-3345} }
Backdoor Mitigation by Distance-Driven Detoxification: Shaokui Wei,

Jiayin Liu,

Hongyuan Zha; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wei_2025_ICCV, author = {Wei, Shaokui and Liu, Jiayin and Zha, Hongyuan}, title = {Backdoor Mitigation by Distance-Driven Detoxification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4465-4474} }
Towards Privacy-preserved Pre-training of Remote Sensing Foundation Models with Federated Mutual-guidance Learning: Jieyi Tan,

Chengwei Zhang,

Bo Dang,

Yansheng Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tan_2025_ICCV, author = {Tan, Jieyi and Zhang, Chengwei and Dang, Bo and Li, Yansheng}, title = {Towards Privacy-preserved Pre-training of Remote Sensing Foundation Models with Federated Mutual-guidance Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1804-1814} }
SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders: Jiahui Geng,

Qing Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Geng_2025_ICCV, author = {Geng, Jiahui and Li, Qing}, title = {SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3023-3033} }
Adversarial Data Augmentation for Single Domain Generalization via Lyapunov Exponent-Guided Optimization: Zuyu Zhang,

Ning Chen,

Yongshan Liu,

Qinghua Zhang,

Xu Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Zuyu and Chen, Ning and Liu, Yongshan and Zhang, Qinghua and Zhang, Xu}, title = {Adversarial Data Augmentation for Single Domain Generalization via Lyapunov Exponent-Guided Optimization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {552-561} }
CMAD: Correlation-Aware and Modalities-Aware Distillation for Multimodal Sentiment Analysis with Missing Modalities: Yan Zhuang,

Minhao Liu,

Wei Bai,

Yanru Zhang,

Xiaoyue Zhang,

Jiawen Deng,

Fuji Ren; [pdf] [supp]
[bibtex]
@InProceedings{Zhuang_2025_ICCV, author = {Zhuang, Yan and Liu, Minhao and Bai, Wei and Zhang, Yanru and Zhang, Xiaoyue and Deng, Jiawen and Ren, Fuji}, title = {CMAD: Correlation-Aware and Modalities-Aware Distillation for Multimodal Sentiment Analysis with Missing Modalities}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4626-4636} }
DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Model: Junjia Huang,

Pengxiang Yan,

Jinhang Cai,

Jiyang Liu,

Zhao Wang,

Yitong Wang,

Xinglong Wu,

Guanbin Li; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2025_ICCV, author = {Huang, Junjia and Yan, Pengxiang and Cai, Jinhang and Liu, Jiyang and Wang, Zhao and Wang, Yitong and Wu, Xinglong and Li, Guanbin}, title = {DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3357-3366} }
FREE-Merging: Fourier Transform for Efficient Model Merging: Shenghe Zheng,

Hongzhi Wang; [pdf] [supp]
[bibtex]
@InProceedings{Zheng_2025_ICCV, author = {Zheng, Shenghe and Wang, Hongzhi}, title = {FREE-Merging: Fourier Transform for Efficient Model Merging}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3863-3873} }
Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers: Zhengyao Lv,

Tianlin Pan,

Chenyang Si,

Zhaoxi Chen,

Wangmeng Zuo,

Ziwei Liu,

Kwan-Yee K. Wong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lv_2025_ICCV, author = {Lv, Zhengyao and Pan, Tianlin and Si, Chenyang and Chen, Zhaoxi and Zuo, Wangmeng and Liu, Ziwei and Wong, Kwan-Yee K.}, title = {Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5934-5943} }
Where am I? Cross-View Geo-localization with Natural Language Descriptions: Junyan Ye,

Honglin Lin,

Leyan Ou,

Dairong Chen,

Zihao Wang,

Qi Zhu,

Conghui He,

Weijia Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Ye_2025_ICCV, author = {Ye, Junyan and Lin, Honglin and Ou, Leyan and Chen, Dairong and Wang, Zihao and Zhu, Qi and He, Conghui and Li, Weijia}, title = {Where am I? Cross-View Geo-localization with Natural Language Descriptions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5890-5900} }
Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration: Junyuan Deng,

Wei Yin,

Xiaoyang Guo,

Qian Zhang,

Xiaotao Hu,

Weiqiang Ren,

Xiao-Xiao Long,

Ping Tan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Deng_2025_ICCV, author = {Deng, Junyuan and Yin, Wei and Guo, Xiaoyang and Zhang, Qian and Hu, Xiaotao and Ren, Weiqiang and Long, Xiao-Xiao and Tan, Ping}, title = {Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7110-7121} }
Multi-view Gaze Target Estimation: Qiaomu Miao,

Vivek Raju Golani,

Jingyi Xu,

Progga Paromita Dutta,

Minh Hoai,

Dimitris Samaras; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Miao_2025_ICCV, author = {Miao, Qiaomu and Golani, Vivek Raju and Xu, Jingyi and Dutta, Progga Paromita and Hoai, Minh and Samaras, Dimitris}, title = {Multi-view Gaze Target Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5371-5381} }
Learning 4D Embodied World Models: Haoyu Zhen,

Qiao Sun,

Hongxin Zhang,

Junyan Li,

Siyuan Zhou,

Yilun Du,

Chuang Gan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhen_2025_ICCV, author = {Zhen, Haoyu and Sun, Qiao and Zhang, Hongxin and Li, Junyan and Zhou, Siyuan and Du, Yilun and Gan, Chuang}, title = {Learning 4D Embodied World Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5337-5347} }
MaskHand: Generative Masked Modeling for Robust Hand Mesh Reconstruction in the Wild: Muhammad Usama Saleem,

Ekkasit Pinyoanuntapong,

Mayur Jagdishbhai Patel,

Hongfei Xue,

Ahmed Helmy,

Srijan Das,

Pu Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Saleem_2025_ICCV, author = {Saleem, Muhammad Usama and Pinyoanuntapong, Ekkasit and Patel, Mayur Jagdishbhai and Xue, Hongfei and Helmy, Ahmed and Das, Srijan and Wang, Pu}, title = {MaskHand: Generative Masked Modeling for Robust Hand Mesh Reconstruction in the Wild}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8372-8383} }
Image-Guided Shape-from-Template Using Mesh Inextensibility Constraints: Thuy Tran,

Ruochen Chen,

Shaifali Parashar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tran_2025_ICCV, author = {Tran, Thuy and Chen, Ruochen and Parashar, Shaifali}, title = {Image-Guided Shape-from-Template Using Mesh Inextensibility Constraints}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7419-7428} }
Confound from All Sides, Distill with Resilience: Multi-Objective Adversarial Paths to Zero-Shot Robustness: Junhao Dong,

Jiao Liu,

Xinghua Qu,

Yew-Soon Ong; [pdf] [supp]
[bibtex]
@InProceedings{Dong_2025_ICCV, author = {Dong, Junhao and Liu, Jiao and Qu, Xinghua and Ong, Yew-Soon}, title = {Confound from All Sides, Distill with Resilience: Multi-Objective Adversarial Paths to Zero-Shot Robustness}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {624-634} }
2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining: Wenqi Zhang,

Hang Zhang,

Xin Li,

Jiashuo Sun,

Yongliang Shen,

Weiming Lu,

Deli Zhao,

Yueting Zhuang,

Lidong Bing; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Wenqi and Zhang, Hang and Li, Xin and Sun, Jiashuo and Shen, Yongliang and Lu, Weiming and Zhao, Deli and Zhuang, Yueting and Bing, Lidong}, title = {2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4647-4658} }
Learning 3D Scene Analogies with Neural Contextual Scene Maps: Junho Kim,

Gwangtak Bae,

Eun Sun Lee,

Young Min Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2025_ICCV, author = {Kim, Junho and Bae, Gwangtak and Lee, Eun Sun and Kim, Young Min}, title = {Learning 3D Scene Analogies with Neural Contextual Scene Maps}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7828-7840} }
FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases: Matteo Poggi,

Fabio Tosi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Poggi_2025_ICCV, author = {Poggi, Matteo and Tosi, Fabio}, title = {FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5667-5679} }
EventUPS: Uncalibrated Photometric Stereo Using an Event Camera: Jinxiu Liang,

Bohan Yu,

Siqi Yang,

Haotian Zhuang,

Jieji Ren,

Peiqi Duan,

Boxin Shi; [pdf] [supp]
[bibtex]
@InProceedings{Liang_2025_ICCV, author = {Liang, Jinxiu and Yu, Bohan and Yang, Siqi and Zhuang, Haotian and Ren, Jieji and Duan, Peiqi and Shi, Boxin}, title = {EventUPS: Uncalibrated Photometric Stereo Using an Event Camera}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7516-7525} }
WildSAT: Learning Satellite Image Representations from Wildlife Observations: Rangel Daroya,

Elijah Cole,

Oisin Mac Aodha,

Grant Van Horn,

Subhransu Maji; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Daroya_2025_ICCV, author = {Daroya, Rangel and Cole, Elijah and Mac Aodha, Oisin and Van Horn, Grant and Maji, Subhransu}, title = {WildSAT: Learning Satellite Image Representations from Wildlife Observations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6143-6154} }
Humans as Checkerboards: Calibrating Camera Motion Scale for World-Coordinate Human Mesh Recovery: Fengyuan Yang,

Kerui Gu,

Ha Linh Nguyen,

Tze Ho Elden Tse,

Angela Yao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Fengyuan and Gu, Kerui and Nguyen, Ha Linh and Tse, Tze Ho Elden and Yao, Angela}, title = {Humans as Checkerboards: Calibrating Camera Motion Scale for World-Coordinate Human Mesh Recovery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6069-6079} }
Deciphering Cross-Modal Alignment in Large Vision-Language Models via Modality Integration Rate: Qidong Huang,

Xiaoyi Dong,

Pan Zhang,

Yuhang Zang,

Yuhang Cao,

Jiaqi Wang,

Weiming Zhang,

Nenghai Yu; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2025_ICCV, author = {Huang, Qidong and Dong, Xiaoyi and Zhang, Pan and Zang, Yuhang and Cao, Yuhang and Wang, Jiaqi and Zhang, Weiming and Yu, Nenghai}, title = {Deciphering Cross-Modal Alignment in Large Vision-Language Models via Modality Integration Rate}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {218-227} }
Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropy: Yunchuan Guan,

Yu Liu,

Ke Zhou,

Zhiqi Shen,

Jenq-Neng Hwang,

Serge Belongie,

Lei Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guan_2025_ICCV, author = {Guan, Yunchuan and Liu, Yu and Zhou, Ke and Shen, Zhiqi and Hwang, Jenq-Neng and Belongie, Serge and Li, Lei}, title = {Is Meta-Learning Out? Rethinking Unsupervised Few-Shot Classification with Limited Entropy}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4188-4197} }
Synergistic Prompting for Robust Visual Recognition with Missing Modalities: Zhihui Zhang,

Luanyuan Dai,

Qika Lin,

Yunfeng Diao,

Guangyin Jin,

Yufei Guo,

Jing Zhang,

Xiaoshuai Hao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Zhihui and Dai, Luanyuan and Lin, Qika and Diao, Yunfeng and Jin, Guangyin and Guo, Yufei and Zhang, Jing and Hao, Xiaoshuai}, title = {Synergistic Prompting for Robust Visual Recognition with Missing Modalities}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1881-1890} }
DAMap: Distance-aware MapNet for High Quality HD Map Construction: Jinpeng Dong,

Chen Li,

Yutong Lin,

Jingwen Fu,

Sanping Zhou,

Nanning Zheng; [pdf] [supp]
[bibtex]
@InProceedings{Dong_2025_ICCV, author = {Dong, Jinpeng and Li, Chen and Lin, Yutong and Fu, Jingwen and Zhou, Sanping and Zheng, Nanning}, title = {DAMap: Distance-aware MapNet for High Quality HD Map Construction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5285-5294} }
ProGait: A Multi-Purpose Video Dataset and Benchmark for Transfemoral Prosthesis Users: Xiangyu Yin,

Boyuan Yang,

Weichen Liu,

Qiyao Xue,

Abrar Alamri,

Goeran Fiedler,

Wei Gao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yin_2025_ICCV, author = {Yin, Xiangyu and Yang, Boyuan and Liu, Weichen and Xue, Qiyao and Alamri, Abrar and Fiedler, Goeran and Gao, Wei}, title = {ProGait: A Multi-Purpose Video Dataset and Benchmark for Transfemoral Prosthesis Users}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8984-8993} }
PseudoMapTrainer: Learning Online Mapping without HD Maps: Christian Löwens,

Thorben Funke,

Jingchao Xie,

Alexandru Paul Condurache; [pdf] [supp]
[bibtex]
@InProceedings{Lowens_2025_ICCV, author = {L\"owens, Christian and Funke, Thorben and Xie, Jingchao and Condurache, Alexandru Paul}, title = {PseudoMapTrainer: Learning Online Mapping without HD Maps}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5263-5272} }
LLM-assisted Entropy-based Adaptive Distillation for Unsupervised Fine-grained Visual Representation Learning: Jianfeng Dong,

Danfeng Luo,

Daizong Liu,

Jie Sun,

Xiaoye Qu,

Xun Yang,

Dongsheng Liu,

Xun Wang; [pdf] [supp]
[bibtex]
@InProceedings{Dong_2025_ICCV, author = {Dong, Jianfeng and Luo, Danfeng and Liu, Daizong and Sun, Jie and Qu, Xiaoye and Yang, Xun and Liu, Dongsheng and Wang, Xun}, title = {LLM-assisted Entropy-based Adaptive Distillation for Unsupervised Fine-grained Visual Representation Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {383-392} }
Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency: Shiji Zhao,

Ranjie Duan,

Fengxiang Wang,

Chi Chen,

Caixin Kang,

Shouwei Ruan,

Jialing Tao,

YueFeng Chen,

Hui Xue,

Xingxing Wei; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2025_ICCV, author = {Zhao, Shiji and Duan, Ranjie and Wang, Fengxiang and Chen, Chi and Kang, Caixin and Ruan, Shouwei and Tao, Jialing and Chen, YueFeng and Xue, Hui and Wei, Xingxing}, title = {Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2045-2054} }
UMDATrack: Unified Multi-Domain Adaptive Tracking Under Adverse Weather Conditions: Siyuan Yao,

Rui Zhu,

Ziqi Wang,

Wenqi Ren,

Yanyang Yan,

Xiaochun Cao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yao_2025_ICCV, author = {Yao, Siyuan and Zhu, Rui and Wang, Ziqi and Ren, Wenqi and Yan, Yanyang and Cao, Xiaochun}, title = {UMDATrack: Unified Multi-Domain Adaptive Tracking Under Adverse Weather Conditions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6466-6475} }
Boosting MLLM Reasoning with Text-Debiased Hint-GRPO: Qihan Huang,

Weilong Dai,

Jinlong Liu,

Wanggui He,

Hao Jiang,

Mingli Song,

Jingyuan Chen,

Chang Yao,

Jie Song; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2025_ICCV, author = {Huang, Qihan and Dai, Weilong and Liu, Jinlong and He, Wanggui and Jiang, Hao and Song, Mingli and Chen, Jingyuan and Yao, Chang and Song, Jie}, title = {Boosting MLLM Reasoning with Text-Debiased Hint-GRPO}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4848-4857} }
Learning on the Go: A Meta-learning Object Navigation Model: Xiaorong Qin,

Xinhang Song,

Sixian Zhang,

Xinyao Yu,

Xinmiao Zhang,

Shuqiang Jiang; [pdf] [supp]
[bibtex]
@InProceedings{Qin_2025_ICCV, author = {Qin, Xiaorong and Song, Xinhang and Zhang, Sixian and Yu, Xinyao and Zhang, Xinmiao and Jiang, Shuqiang}, title = {Learning on the Go: A Meta-learning Object Navigation Model}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8939-8949} }
PriOr-Flow: Enhancing Primitive Panoramic Optical Flow with Orthogonal View: Longliang Liu,

Miaojie Feng,

Junda Cheng,

Jijun Xiang,

Xuan Zhu,

Xin Yang; [pdf]
[bibtex]
@InProceedings{Liu_2025_ICCV, author = {Liu, Longliang and Feng, Miaojie and Cheng, Junda and Xiang, Jijun and Zhu, Xuan and Yang, Xin}, title = {PriOr-Flow: Enhancing Primitive Panoramic Optical Flow with Orthogonal View}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5326-5336} }
A Simple yet Mighty Hartley Diffusion Versatilist for Generalizable Dense Vision Tasks: Qi Bi,

Jingjun Yi,

Huimin Huang,

Hao Zheng,

Haolan Zhan,

Wei Ji,

Yawen Huang,

Yuexiang Li,

Yefeng Zheng; [pdf] [supp]
[bibtex]
@InProceedings{Bi_2025_ICCV, author = {Bi, Qi and Yi, Jingjun and Huang, Huimin and Zheng, Hao and Zhan, Haolan and Ji, Wei and Huang, Yawen and Li, Yuexiang and Zheng, Yefeng}, title = {A Simple yet Mighty Hartley Diffusion Versatilist for Generalizable Dense Vision Tasks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6748-6760} }
LGA-Net: Learning Local and Global Affinities for Sparse Scribble based Image Colorization: Hongjin Lyu,

Bo Li,

Paul L. Rosin,

Yu-Kun Lai; [pdf] [supp]
[bibtex]
@InProceedings{Lyu_2025_ICCV, author = {Lyu, Hongjin and Li, Bo and Rosin, Paul L. and Lai, Yu-Kun}, title = {LGA-Net: Learning Local and Global Affinities for Sparse Scribble based Image Colorization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8144-8153} }
ScoreHOI: Physically Plausible Reconstruction of Human-Object Interaction via Score-Guided Diffusion: Ao Li,

Jinpeng Liu,

Yixuan Zhu,

Yansong Tang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Ao and Liu, Jinpeng and Zhu, Yixuan and Tang, Yansong}, title = {ScoreHOI: Physically Plausible Reconstruction of Human-Object Interaction via Score-Guided Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7592-7602} }
CMB-ML: A Cosmic Microwave Background Dataset for the Oldest Possible Computer Vision Task: James Amato,

Yunan Xie,

Leonel Medina-Varela,

Ammar Aljerwi,

Adam McCutcheon,

T. Seth Rippentrop,

Kristian Gonzalez,

Jacques Delabrouille,

Mustapha Ishak,

Nicholas Ruozzi; [pdf] [supp]
[bibtex]
@InProceedings{Amato_2025_ICCV, author = {Amato, James and Xie, Yunan and Medina-Varela, Leonel and Aljerwi, Ammar and McCutcheon, Adam and Rippentrop, T. Seth and Gonzalez, Kristian and Delabrouille, Jacques and Ishak, Mustapha and Ruozzi, Nicholas}, title = {CMB-ML: A Cosmic Microwave Background Dataset for the Oldest Possible Computer Vision Task}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9418-9430} }
Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction: Edgar Sucar,

Zihang Lai,

Eldar Insafutdinov,

Andrea Vedaldi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sucar_2025_ICCV, author = {Sucar, Edgar and Lai, Zihang and Insafutdinov, Eldar and Vedaldi, Andrea}, title = {Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7295-7305} }
Toward Material-Agnostic System Identification from Videos: Yizhou Zhao,

Haoyu Chen,

Chunjiang Liu,

Zhenyang Li,

Charles Herrmann,

Junhwa Hur,

Yinxiao Li,

Ming-Hsuan Yang,

Bhiksha Raj,

Min Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2025_ICCV, author = {Zhao, Yizhou and Chen, Haoyu and Liu, Chunjiang and Li, Zhenyang and Herrmann, Charles and Hur, Junhwa and Li, Yinxiao and Yang, Ming-Hsuan and Raj, Bhiksha and Xu, Min}, title = {Toward Material-Agnostic System Identification from Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5944-5956} }
Robust 3D-Masked Part-level Editing in 3D Gaussian Splatting with Regularized Score Distillation Sampling: Hayeon Kim,

Ji Ha Jang,

Se Young Chun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2025_ICCV, author = {Kim, Hayeon and Jang, Ji Ha and Chun, Se Young}, title = {Robust 3D-Masked Part-level Editing in 3D Gaussian Splatting with Regularized Score Distillation Sampling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5501-5510} }
Effective Training Data Synthesis for Improving MLLM Chart Understanding: Yuwei Yang,

Zeyu Zhang,

Yunzhong Hou,

Zhuowan Li,

Gaowen Liu,

Ali Payani,

Yuan-Sen Ting,

Liang Zheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Yuwei and Zhang, Zeyu and Hou, Yunzhong and Li, Zhuowan and Liu, Gaowen and Payani, Ali and Ting, Yuan-Sen and Zheng, Liang}, title = {Effective Training Data Synthesis for Improving MLLM Chart Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2653-2663} }
Neural Architecture Search Driven by Locally Guided Diffusion for Personalized Federated Learning: Peng Liao,

Xilu Wang,

Yaochu Jin,

Wenli Du,

Han Hu; [pdf] [supp]
[bibtex]
@InProceedings{Liao_2025_ICCV, author = {Liao, Peng and Wang, Xilu and Jin, Yaochu and Du, Wenli and Hu, Han}, title = {Neural Architecture Search Driven by Locally Guided Diffusion for Personalized Federated Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4222-4231} }
ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning: Mingqi Yuan,

Bo Li,

Xin Jin,

Wenjun Zeng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yuan_2025_ICCV, author = {Yuan, Mingqi and Li, Bo and Jin, Xin and Zeng, Wenjun}, title = {ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2620-2630} }
GenieBlue: Integrating both Linguistic and Multimodal Capabilities for Large Language Models on Mobile Devices: Xudong Lu,

Yinghao Chen,

Renshou Wu,

Haohao Gao,

Xi Chen,

Xue Yang,

Xiangyu Zhao,

Aojun Zhou,

Fangyuan Li,

Yafei Wen,

Xiaoxin Chen,

Shuai Ren,

Hongsheng Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2025_ICCV, author = {Lu, Xudong and Chen, Yinghao and Wu, Renshou and Gao, Haohao and Chen, Xi and Yang, Xue and Zhao, Xiangyu and Zhou, Aojun and Li, Fangyuan and Wen, Yafei and Chen, Xiaoxin and Ren, Shuai and Li, Hongsheng}, title = {GenieBlue: Integrating both Linguistic and Multimodal Capabilities for Large Language Models on Mobile Devices}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4198-4210} }
MambaML: Exploring State Space Models for Multi-Label Image Classification: Xuelin Zhu,

Jian Liu,

Jiuxin Cao,

Bing Wang; [pdf] [supp]
[bibtex]
@InProceedings{Zhu_2025_ICCV, author = {Zhu, Xuelin and Liu, Jian and Cao, Jiuxin and Wang, Bing}, title = {MambaML: Exploring State Space Models for Multi-Label Image Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4743-4753} }
CO2-Net: A Physics-Informed Spatio-Temporal Model for Global Surface CO2 Reconstruction: Hao Zheng,

Yuting Zheng,

Hanbo Huang,

Chaofan Sun,

Enhui Liao,

Lin Liu,

Yi Han,

Hao Zhou,

Shiyu Liang; [pdf] [supp]
[bibtex]
@InProceedings{Zheng_2025_ICCV, author = {Zheng, Hao and Zheng, Yuting and Huang, Hanbo and Sun, Chaofan and Liao, Enhui and Liu, Lin and Han, Yi and Zhou, Hao and Liang, Shiyu}, title = {CO2-Net: A Physics-Informed Spatio-Temporal Model for Global Surface CO2 Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6220-6230} }
Variance-Based Pruning for Accelerating and Compressing Trained Networks: Uranik Berisha,

Jens Mehnert,

Alexandru Paul Condurache; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Berisha_2025_ICCV, author = {Berisha, Uranik and Mehnert, Jens and Condurache, Alexandru Paul}, title = {Variance-Based Pruning for Accelerating and Compressing Trained Networks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4973-4982} }
Learning Normal Flow Directly From Events: Dehao Yuan,

Levi Burner,

Jiayi Wu,

Minghui Liu,

Jingxi Chen,

Yiannis Aloimonos,

Cornelia Fermüller; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yuan_2025_ICCV, author = {Yuan, Dehao and Burner, Levi and Wu, Jiayi and Liu, Minghui and Chen, Jingxi and Aloimonos, Yiannis and Ferm\"uller, Cornelia}, title = {Learning Normal Flow Directly From Events}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7969-7979} }
Federated Prompt-Tuning with Heterogeneous and Incomplete Multimodal Client Data: Thu Hang Phung,

Duong M. Nguyen,

Thanh Trung Huynh,

Quoc Viet Hung Nguyen,

Trong Nghia Hoang,

Phi Le Nguyen; [pdf] [supp]
[bibtex]
@InProceedings{Phung_2025_ICCV, author = {Phung, Thu Hang and Nguyen, Duong M. and Huynh, Thanh Trung and Nguyen, Quoc Viet Hung and Hoang, Trong Nghia and Le Nguyen, Phi}, title = {Federated Prompt-Tuning with Heterogeneous and Incomplete Multimodal Client Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3936-3946} }
Trace3D: Consistent Segmentation Lifting via Gaussian Instance Tracing: Hongyu Shen,

Junfeng Ni,

Yixin Chen,

Weishuo Li,

Mingtao Pei,

Siyuan Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shen_2025_ICCV, author = {Shen, Hongyu and Ni, Junfeng and Chen, Yixin and Li, Weishuo and Pei, Mingtao and Huang, Siyuan}, title = {Trace3D: Consistent Segmentation Lifting via Gaussian Instance Tracing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6656-6666} }
LMM-Det: Make Large Multimodal Models Excel in Object Detection: Jincheng Li,

Chunyu Xie,

Ji Ao,

Dawei Leng,

Yuhui Yin; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Jincheng and Xie, Chunyu and Ao, Ji and Leng, Dawei and Yin, Yuhui}, title = {LMM-Det: Make Large Multimodal Models Excel in Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {308-318} }
Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment: Kejia Zhang,

Juanjuan Weng,

Shaozi Li,

Zhiming Luo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Kejia and Weng, Juanjuan and Li, Shaozi and Luo, Zhiming}, title = {Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2783-2792} }
FiffDepth: Feed-forward Transformation of Diffusion-Based Generators for Detailed Depth Estimation: Yunpeng Bai,

Qixing Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bai_2025_ICCV, author = {Bai, Yunpeng and Huang, Qixing}, title = {FiffDepth: Feed-forward Transformation of Diffusion-Based Generators for Detailed Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6023-6033} }
Reinforcement Learning-Guided Data Selection via Redundancy Assessment: Suorong Yang,

Peijia Li,

Furao Shen,

Jian Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Suorong and Li, Peijia and Shen, Furao and Zhao, Jian}, title = {Reinforcement Learning-Guided Data Selection via Redundancy Assessment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1004-1015} }
Optical Model-Driven Sharpness Mapping for Autofocus in Small Depth-of-Field and Severe Defocus Scenarios: Chen-Liang Fan,

Mingpei Cao,

Chih Chien Hung,

Yuesheng Zhu; [pdf] [supp]
[bibtex]
@InProceedings{Fan_2025_ICCV, author = {Fan, Chen-Liang and Cao, Mingpei and Hung, Chih Chien and Zhu, Yuesheng}, title = {Optical Model-Driven Sharpness Mapping for Autofocus in Small Depth-of-Field and Severe Defocus Scenarios}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6426-6435} }
Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks: Jiawei Wang,

Yushen Zuo,

Yuanjun Chai,

Zhendong Liu,

Yicheng Fu,

Yichun Feng,

Kin-Man Lam; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Jiawei and Zuo, Yushen and Chai, Yuanjun and Liu, Zhendong and Fu, Yicheng and Feng, Yichun and Lam, Kin-Man}, title = {Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2773-2782} }
NAPPure: Adversarial Purification for Robust Image Classification under Non-Additive Perturbations: Junjie Nan,

Jianing Li,

Wei Chen,

Mingkun Zhang,

Xueqi Cheng; [pdf] [supp]
[bibtex]
@InProceedings{Nan_2025_ICCV, author = {Nan, Junjie and Li, Jianing and Chen, Wei and Zhang, Mingkun and Cheng, Xueqi}, title = {NAPPure: Adversarial Purification for Robust Image Classification under Non-Additive Perturbations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2260-2269} }
MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGI: Huanjin Yao,

Jiaxing Huang,

Yawen Qiu,

Michael K. Chen,

Wenzheng Liu,

Wei Zhang,

Wenjie Zeng,

Xikun Zhang,

Jingyi Zhang,

YuXin Song,

Wenhao Wu,

Dacheng Tao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yao_2025_ICCV, author = {Yao, Huanjin and Huang, Jiaxing and Qiu, Yawen and Chen, Michael K. and Liu, Wenzheng and Zhang, Wei and Zeng, Wenjie and Zhang, Xikun and Zhang, Jingyi and Song, YuXin and Wu, Wenhao and Tao, Dacheng}, title = {MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGI}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {273-283} }
Dual Reciprocal Learning of Language-based Human Motion Understanding and Generation: Chen Liang,

Zhicheng Shi,

Wenguan Wang,

Yi Yang; [pdf] [supp]
[bibtex]
@InProceedings{Liang_2025_ICCV, author = {Liang, Chen and Shi, Zhicheng and Wang, Wenguan and Yang, Yi}, title = {Dual Reciprocal Learning of Language-based Human Motion Understanding and Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6252-6262} }
To Label or Not to Label: PALM - A Predictive Model for Evaluating Sample Efficiency in Active Learning Models: Julia Machnio,

Mads Nielsen,

Mostafa Mehdipour Ghazi; [pdf] [supp]
[bibtex]
@InProceedings{Machnio_2025_ICCV, author = {Machnio, Julia and Nielsen, Mads and Ghazi, Mostafa Mehdipour}, title = {To Label or Not to Label: PALM - A Predictive Model for Evaluating Sample Efficiency in Active Learning Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4039-4048} }
Dynamic Multimodal Prototype Learning in Vision-Language Models: Xingyu Zhu,

Shuo Wang,

Beier Zhu,

Miaoge Li,

Yunfan Li,

Junfeng Fang,

Zhicai Wang,

Dongsheng Wang,

Hanwang Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhu_2025_ICCV, author = {Zhu, Xingyu and Wang, Shuo and Zhu, Beier and Li, Miaoge and Li, Yunfan and Fang, Junfeng and Wang, Zhicai and Wang, Dongsheng and Zhang, Hanwang}, title = {Dynamic Multimodal Prototype Learning in Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2501-2511} }
Client2Vec: Improving Federated Learning by Distribution Shifts Aware Client Indexing: Yongxin Guo,

Lin Wang,

Xiaoying Tang,

Tao Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2025_ICCV, author = {Guo, Yongxin and Wang, Lin and Tang, Xiaoying and Lin, Tao}, title = {Client2Vec: Improving Federated Learning by Distribution Shifts Aware Client Indexing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1433-1443} }
FuXi-RTM: A Physics-Guided Prediction Framework with Radiative Transfer Modeling: Qiusheng Huang,

Xiaohui Zhong,

Xu Fan,

Hao Li; [pdf]
[bibtex]
@InProceedings{Huang_2025_ICCV, author = {Huang, Qiusheng and Zhong, Xiaohui and Fan, Xu and Li, Hao}, title = {FuXi-RTM: A Physics-Guided Prediction Framework with Radiative Transfer Modeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8852-8862} }
Loss Functions for Predictor-based Neural Architecture Search: Han Ji,

Yuqi Feng,

Jiahao Fan,

Yanan Sun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ji_2025_ICCV, author = {Ji, Han and Feng, Yuqi and Fan, Jiahao and Sun, Yanan}, title = {Loss Functions for Predictor-based Neural Architecture Search}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1624-1633} }
Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension: Xiyao Wang,

Zhengyuan Yang,

Linjie Li,

Hongjin Lu,

Yuancheng Xu,

Chung-Ching Lin,

Kevin Lin,

Furong Huang,

Lijuan Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Xiyao and Yang, Zhengyuan and Li, Linjie and Lu, Hongjin and Xu, Yuancheng and Lin, Chung-Ching and Lin, Kevin and Huang, Furong and Wang, Lijuan}, title = {Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1173-1184} }
Cooperative Pseudo Labeling for Unsupervised Federated Classification: Kuangpu Guo,

Lijun Sheng,

Yongcan Yu,

Jian Liang,

Zilei Wang,

Ran He; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2025_ICCV, author = {Guo, Kuangpu and Sheng, Lijun and Yu, Yongcan and Liang, Jian and Wang, Zilei and He, Ran}, title = {Cooperative Pseudo Labeling for Unsupervised Federated Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3326-3336} }
FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment: Hang Xu,

Jie Huang,

Linjiang Huang,

Dong Li,

Yidi Liu,

Feng Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2025_ICCV, author = {Xu, Hang and Huang, Jie and Huang, Linjiang and Li, Dong and Liu, Yidi and Zhao, Feng}, title = {FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3268-3279} }
Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations: Jeong Hun Yeo,

Minsu Kim,

Chae Won Kim,

Stavros Petridis,

Yong Man Ro; [pdf] [supp]
[bibtex]
@InProceedings{Yeo_2025_ICCV, author = {Yeo, Jeong Hun and Kim, Minsu and Kim, Chae Won and Petridis, Stavros and Ro, Yong Man}, title = {Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6693-6703} }
Supervised Exploratory Learning for Long-Tailed Visual Recognition: Zhongquan Jian,

Yanhao Chen,

Yancheng Wang,

Junfeng Yao,

Meihong Wang,

Qingqiang Wu; [pdf]
[bibtex]
@InProceedings{Jian_2025_ICCV, author = {Jian, Zhongquan and Chen, Yanhao and Wang, Yancheng and Yao, Junfeng and Wang, Meihong and Wu, Qingqiang}, title = {Supervised Exploratory Learning for Long-Tailed Visual Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1870-1880} }
Enhanced Event-based Dense Stereo via Cross-Sensor Knowledge Distillation: Haihao Zhang,

Yunjian Zhang,

Jianing Li,

Lin Zhu,

Meng Lv,

Yao Zhu,

Yanwei Liu,

Xiangyang Ji; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Haihao and Zhang, Yunjian and Li, Jianing and Zhu, Lin and Lv, Meng and Zhu, Yao and Liu, Yanwei and Ji, Xiangyang}, title = {Enhanced Event-based Dense Stereo via Cross-Sensor Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5437-5447} }
Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning: Qi Wang,

Zhipeng Zhang,

Baao Xie,

Xin Jin,

Yunbo Wang,

Shiyu Wang,

Liaomo Zheng,

Xiaokang Yang,

Wenjun Zeng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Qi and Zhang, Zhipeng and Xie, Baao and Jin, Xin and Wang, Yunbo and Wang, Shiyu and Zheng, Liaomo and Yang, Xiaokang and Zeng, Wenjun}, title = {Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2599-2608} }
When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning: Junwei Luo,

Yingying Zhang,

Xue Yang,

Kang Wu,

Qi Zhu,

Lei Liang,

Jingdong Chen,

Yansheng Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Luo_2025_ICCV, author = {Luo, Junwei and Zhang, Yingying and Yang, Xue and Wu, Kang and Zhu, Qi and Liang, Lei and Chen, Jingdong and Li, Yansheng}, title = {When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9206-9217} }
Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis: Chen Zhao,

Xuan Wang,

Tong Zhang,

Saqib Javed,

Mathieu Salzmann; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhao_2025_ICCV, author = {Zhao, Chen and Wang, Xuan and Zhang, Tong and Javed, Saqib and Salzmann, Mathieu}, title = {Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4940-4950} }
CAD-Recode: Reverse Engineering CAD Code from Point Clouds: Danila Rukhovich,

Elona Dupont,

Dimitrios Mallis,

Kseniya Cherenkova,

Anis Kacem,

Djamila Aouada; [pdf] [supp]
[bibtex]
@InProceedings{Rukhovich_2025_ICCV, author = {Rukhovich, Danila and Dupont, Elona and Mallis, Dimitrios and Cherenkova, Kseniya and Kacem, Anis and Aouada, Djamila}, title = {CAD-Recode: Reverse Engineering CAD Code from Point Clouds}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9801-9811} }
ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectives: Yuqian Fu,

Runze Wang,

Bin Ren,

Guolei Sun,

Biao Gong,

Yanwei Fu,

Danda Pani Paudel,

Xuanjing Huang,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fu_2025_ICCV, author = {Fu, Yuqian and Wang, Runze and Ren, Bin and Sun, Guolei and Gong, Biao and Fu, Yanwei and Paudel, Danda Pani and Huang, Xuanjing and Van Gool, Luc}, title = {ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectives}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6530-6540} }
Bring Your Rear Cameras for Egocentric 3D Human Pose Estimation: Hiroyasu Akada,

Jian Wang,

Vladislav Golyanik,

Christian Theobalt; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Akada_2025_ICCV, author = {Akada, Hiroyasu and Wang, Jian and Golyanik, Vladislav and Theobalt, Christian}, title = {Bring Your Rear Cameras for Egocentric 3D Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9497-9507} }
Federated Continual Instruction Tuning: Haiyang Guo,

Fanhu Zeng,

Fei Zhu,

Wenzhuo Liu,

Da-Han Wang,

Jian Xu,

Xu-Yao Zhang,

Cheng-Lin Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2025_ICCV, author = {Guo, Haiyang and Zeng, Fanhu and Zhu, Fei and Liu, Wenzhuo and Wang, Da-Han and Xu, Jian and Zhang, Xu-Yao and Liu, Cheng-Lin}, title = {Federated Continual Instruction Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1325-1335} }
What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization: Xavier Thomas,

Deepti Ghadiyaram; [pdf] [supp]
[bibtex]
@InProceedings{Thomas_2025_ICCV, author = {Thomas, Xavier and Ghadiyaram, Deepti}, title = {What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2183-2194} }
Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation: Yooshin Cho,

Hanbyel Cho,

Janghyeon Lee,

HyeongGwon Hong,

Jaesung Ahn,

Junmo Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cho_2025_ICCV, author = {Cho, Yooshin and Cho, Hanbyel and Lee, Janghyeon and Hong, HyeongGwon and Ahn, Jaesung and Kim, Junmo}, title = {Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4550-4560} }
Towards Cross-modal Backward-compatible Representation Learning for Vision-Language Models: Young Kyun Jang,

Ser-nam Lim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jang_2025_ICCV, author = {Jang, Young Kyun and Lim, Ser-nam}, title = {Towards Cross-modal Backward-compatible Representation Learning for Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1783-1792} }
Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation: Guopeng Li,

Qiang Wang,

Ke Yan,

Shouhong Ding,

Yuan Gao,

Gui-Song Xia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Guopeng and Wang, Qiang and Yan, Ke and Ding, Shouhong and Gao, Yuan and Xia, Gui-Song}, title = {Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3445-3454} }
Dual Domain Control via Active Learning for Remote Sensing Domain Incremental Object Detection: Jiachen Sun,

De Cheng,

Xi Yang,

Nannan Wang; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2025_ICCV, author = {Sun, Jiachen and Cheng, De and Yang, Xi and Wang, Nannan}, title = {Dual Domain Control via Active Learning for Remote Sensing Domain Incremental Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3809-3818} }
GRAB: A Challenging GRaph Analysis Benchmark for Large Multimodal Models: Jonathan Roberts,

Kai Han,

Samuel Albanie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Roberts_2025_ICCV, author = {Roberts, Jonathan and Han, Kai and Albanie, Samuel}, title = {GRAB: A Challenging GRaph Analysis Benchmark for Large Multimodal Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1644-1654} }
Transparent Vision: A Theory of Hierarchical Invariant Representations: Shuren Qi,

Yushu Zhang,

Chao Wang,

Zhihua Xia,

Xiaochun Cao,

Fenglei Fan; [pdf] [supp]
[bibtex]
@InProceedings{Qi_2025_ICCV, author = {Qi, Shuren and Zhang, Yushu and Wang, Chao and Xia, Zhihua and Cao, Xiaochun and Fan, Fenglei}, title = {Transparent Vision: A Theory of Hierarchical Invariant Representations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3435-3444} }
Multi-View 3D Point Tracking: Frano Rajič,

Haofei Xu,

Marko Mihajlovic,

Siyuan Li,

Irem Demir,

Emircan Gündoğdu,

Lei Ke,

Sergey Prokudin,

Marc Pollefeys,

Siyu Tang; [pdf] [supp]
[bibtex]
@InProceedings{Rajic_2025_ICCV, author = {Raji\v{c}, Frano and Xu, Haofei and Mihajlovic, Marko and Li, Siyuan and Demir, Irem and G\"undo\u{g}du, Emircan and Ke, Lei and Prokudin, Sergey and Pollefeys, Marc and Tang, Siyu}, title = {Multi-View 3D Point Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {59-68} }
Scaling 3D Compositional Models for Robust Classification and Pose Estimation: Xiaoding Yuan,

Guofeng Zhang,

Prakhar Kaushik,

Artur Jesslen,

Adam Kortylewski,

Alan Yuille; [pdf] [supp]
[bibtex]
@InProceedings{Yuan_2025_ICCV, author = {Yuan, Xiaoding and Zhang, Guofeng and Kaushik, Prakhar and Jesslen, Artur and Kortylewski, Adam and Yuille, Alan}, title = {Scaling 3D Compositional Models for Robust Classification and Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6406-6415} }
MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models: Young-Jun Lee,

Byung-Kwan Lee,

Jianshu Zhang,

Yechan Hwang,

Byungsoo Ko,

Han-Gyu Kim,

Dongyu Yao,

Xuankun Rong,

Eojin Joo,

Seung-Ho Han,

Bowon Ko,

Ho-Jin Choi; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2025_ICCV, author = {Lee, Young-Jun and Lee, Byung-Kwan and Zhang, Jianshu and Hwang, Yechan and Ko, Byungsoo and Kim, Han-Gyu and Yao, Dongyu and Rong, Xuankun and Joo, Eojin and Han, Seung-Ho and Ko, Bowon and Choi, Ho-Jin}, title = {MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {708-719} }
Contact-Aware Refinement of Human Pose Pseudo-Ground Truth via Bioimpedance Sensing: Maria-Paola Forte,

Nikos Athanasiou,

Giulia Ballardini,

Jan Ulrich Bartels,

Katherine J. Kuchenbecker,

Michael J. Black; [pdf]
[bibtex]
@InProceedings{Forte_2025_ICCV, author = {Forte, Maria-Paola and Athanasiou, Nikos and Ballardini, Giulia and Bartels, Jan Ulrich and Kuchenbecker, Katherine J. and Black, Michael J.}, title = {Contact-Aware Refinement of Human Pose Pseudo-Ground Truth via Bioimpedance Sensing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5071-5080} }
Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding: Yue Fan,

Xiaojian Ma,

Rongpeng Su,

Jun Guo,

Rujie Wu,

Xi Chen,

Qing Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fan_2025_ICCV, author = {Fan, Yue and Ma, Xiaojian and Su, Rongpeng and Guo, Jun and Wu, Rujie and Chen, Xi and Li, Qing}, title = {Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6342-6352} }
PRO-VPT: Distribution-Adaptive Visual Prompt Tuning via Prompt Relocation: Chikai Shang,

Mengke Li,

Yiqun Zhang,

Zhen Chen,

Jinlin Wu,

Fangqing Gu,

Yang Lu,

Yiu-Ming Cheung; [pdf] [supp]
[bibtex]
@InProceedings{Shang_2025_ICCV, author = {Shang, Chikai and Li, Mengke and Zhang, Yiqun and Chen, Zhen and Wu, Jinlin and Gu, Fangqing and Lu, Yang and Cheung, Yiu-Ming}, title = {PRO-VPT: Distribution-Adaptive Visual Prompt Tuning via Prompt Relocation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1558-1568} }
AdaDrive: Self-Adaptive Slow-Fast System for Language-Grounded Autonomous Driving: Ruifei Zhang,

Junlin Xie,

Wei Zhang,

Weikai Chen,

Xiao Tan,

Xiang Wan,

Guanbin Li; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Ruifei and Xie, Junlin and Zhang, Wei and Chen, Weikai and Tan, Xiao and Wan, Xiang and Li, Guanbin}, title = {AdaDrive: Self-Adaptive Slow-Fast System for Language-Grounded Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5112-5121} }
A Linear N-Point Solver for Structure and Motion from Asynchronous Tracks: Hang Su,

Yunlong Feng,

Daniel Gehrig,

Panfeng Jiang,

Ling Gao,

Xavier Lagorce,

Laurent Kneip; [pdf] [supp]
[bibtex]
@InProceedings{Su_2025_ICCV, author = {Su, Hang and Feng, Yunlong and Gehrig, Daniel and Jiang, Panfeng and Gao, Ling and Lagorce, Xavier and Kneip, Laurent}, title = {A Linear N-Point Solver for Structure and Motion from Asynchronous Tracks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4339-4348} }
Unleashing Vecset Diffusion Model for Fast Shape Generation: Zeqiang Lai,

Yunfei Zhao,

Zibo Zhao,

Haolin Liu,

Fuyun Wang,

Huiwen Shi,

Xianghui Yang,

Qingxiang Lin,

Jingwei Huang,

Yuhong Liu,

Jie Jiang,

Chunchao Guo,

Xiangyu Yue; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lai_2025_ICCV, author = {Lai, Zeqiang and Zhao, Yunfei and Zhao, Zibo and Liu, Haolin and Wang, Fuyun and Shi, Huiwen and Yang, Xianghui and Lin, Qingxiang and Huang, Jingwei and Liu, Yuhong and Jiang, Jie and Guo, Chunchao and Yue, Xiangyu}, title = {Unleashing Vecset Diffusion Model for Fast Shape Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2523-2533} }
RayZer: A Self-supervised Large View Synthesis Model: Hanwen Jiang,

Hao Tan,

Peng Wang,

Haian Jin,

Yue Zhao,

Sai Bi,

Kai Zhang,

Fujun Luan,

Kalyan Sunkavalli,

Qixing Huang,

Georgios Pavlakos; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2025_ICCV, author = {Jiang, Hanwen and Tan, Hao and Wang, Peng and Jin, Haian and Zhao, Yue and Bi, Sai and Zhang, Kai and Luan, Fujun and Sunkavalli, Kalyan and Huang, Qixing and Pavlakos, Georgios}, title = {RayZer: A Self-supervised Large View Synthesis Model}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4918-4929} }
Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels: Olaf Dünkel,

Thomas Wimmer,

Christian Theobalt,

Christian Rupprecht,

Adam Kortylewski; [pdf] [supp]
[bibtex]
@InProceedings{Dunkel_2025_ICCV, author = {D\"unkel, Olaf and Wimmer, Thomas and Theobalt, Christian and Rupprecht, Christian and Kortylewski, Adam}, title = {Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5834-5844} }
DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmetic: Munish Monga,

Vishal Chudasama,

Pankaj Wasnik,

Biplab Banerjee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Monga_2025_ICCV, author = {Monga, Munish and Chudasama, Vishal and Wasnik, Pankaj and Banerjee, Biplab}, title = {DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmetic}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3121-3131} }
BATCLIP: Bimodal Online Test-Time Adaptation for CLIP: Sarthak Maharana,

Baoming Zhang,

Leonid Karlinsky,

Rogerio Feris,

Yunhui Guo; [pdf] [supp]
[bibtex]
@InProceedings{Maharana_2025_ICCV, author = {Maharana, Sarthak and Zhang, Baoming and Karlinsky, Leonid and Feris, Rogerio and Guo, Yunhui}, title = {BATCLIP: Bimodal Online Test-Time Adaptation for CLIP}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1569-1579} }
SHIFT: Smoothing Hallucinations by Information Flow Tuning for Multimodal Large Language Models: Sudong Wang,

Yunjian Zhang,

Yao Zhu,

Enci Liu,

Jianing Li,

Yanwei Liu,

Xiangyang Ji; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Sudong and Zhang, Yunjian and Zhu, Yao and Liu, Enci and Li, Jianing and Liu, Yanwei and Ji, Xiangyang}, title = {SHIFT: Smoothing Hallucinations by Information Flow Tuning for Multimodal Large Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3639-3649} }
DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundness: Ruining Li,

Chuanxia Zheng,

Christian Rupprecht,

Andrea Vedaldi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Ruining and Zheng, Chuanxia and Rupprecht, Christian and Vedaldi, Andrea}, title = {DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundness}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6772-6783} }
LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal: Shr-Ruei Tsai,

Wei-Cheng Chang,

Jie-Ying Lee,

Chih-Hai Su,

Yu-Lun Liu; [pdf] [supp]
[bibtex]
@InProceedings{Tsai_2025_ICCV, author = {Tsai, Shr-Ruei and Chang, Wei-Cheng and Lee, Jie-Ying and Su, Chih-Hai and Liu, Yu-Lun}, title = {LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6353-6363} }
From Holistic to Localized: Local Enhanced Adapters for Efficient Visual Instruction Fine-Tuning: Pengkun Jiao,

Bin Zhu,

Jingjing Chen,

Chong-Wah Ngo,

Yu-Gang Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiao_2025_ICCV, author = {Jiao, Pengkun and Zhu, Bin and Chen, Jingjing and Ngo, Chong-Wah and Jiang, Yu-Gang}, title = {From Holistic to Localized: Local Enhanced Adapters for Efficient Visual Instruction Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2728-2737} }
Diorama: Unleashing Zero-shot Single-view 3D Indoor Scene Modeling: Qirui Wu,

Denys Iliash,

Daniel Ritchie,

Manolis Savva,

Angel X. Chang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2025_ICCV, author = {Wu, Qirui and Iliash, Denys and Ritchie, Daniel and Savva, Manolis and Chang, Angel X.}, title = {Diorama: Unleashing Zero-shot Single-view 3D Indoor Scene Modeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8896-8907} }
Boosting Multi-View Indoor 3D Object Detection via Adaptive 3D Volume Construction: Runmin Zhang,

Zhu Yu,

Si-Yuan Cao,

Lingyu Zhu,

Guangyi Zhang,

Xiaokai Bai,

Hui-Liang Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Runmin and Yu, Zhu and Cao, Si-Yuan and Zhu, Lingyu and Zhang, Guangyi and Bai, Xiaokai and Shen, Hui-Liang}, title = {Boosting Multi-View Indoor 3D Object Detection via Adaptive 3D Volume Construction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5980-5989} }
Learning Separable Fine-Grained Representation via Dendrogram Construction from Coarse Labels for Fine-grained Visual Recognition: Guanghui Shi,

Xuefeng Liang,

Wenjie Li,

Xiaoyu Lin; [pdf] [supp]
[bibtex]
@InProceedings{Shi_2025_ICCV, author = {Shi, Guanghui and Liang, Xuefeng and Li, Wenjie and Lin, Xiaoyu}, title = {Learning Separable Fine-Grained Representation via Dendrogram Construction from Coarse Labels for Fine-grained Visual Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {870-879} }
DyGS-SLAM: Real-Time Accurate Localization and Gaussian Reconstruction for Dynamic Scenes: Xinggang Hu,

Chenyangguang Zhang,

Mingyuan Zhao,

Yuanze Gui,

Xiangkui Zhang,

Xiangyang Ji; [pdf] [supp]
[bibtex]
@InProceedings{Hu_2025_ICCV, author = {Hu, Xinggang and Zhang, Chenyangguang and Zhao, Mingyuan and Gui, Yuanze and Zhang, Xiangkui and Ji, Xiangyang}, title = {DyGS-SLAM: Real-Time Accurate Localization and Gaussian Reconstruction for Dynamic Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9561-9571} }
MCAM: Multimodal Causal Analysis Model for Ego-Vehicle-Level Driving Video Understanding: Tongtong Cheng,

Rongzhen Li,

Yixin Xiong,

Tao Zhang,

Jing Wang,

Kai Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Cheng_2025_ICCV, author = {Cheng, Tongtong and Li, Rongzhen and Xiong, Yixin and Zhang, Tao and Wang, Jing and Liu, Kai}, title = {MCAM: Multimodal Causal Analysis Model for Ego-Vehicle-Level Driving Video Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5479-5489} }
Adversarial Robust Memory-Based Continual Learner: Xiaoyue Mi,

Fan Tang,

Zonghan Yang,

Danding Wang,

Juan Cao,

Peng Li,

Yang Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mi_2025_ICCV, author = {Mi, Xiaoyue and Tang, Fan and Yang, Zonghan and Wang, Danding and Cao, Juan and Li, Peng and Liu, Yang}, title = {Adversarial Robust Memory-Based Continual Learner}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {562-572} }
Gradient Short-Circuit: Efficient Out-of-Distribution Detection via Feature Intervention: Jiawei Gu,

Ziyue Qiao,

Zechao Li; [pdf] [supp]
[bibtex]
@InProceedings{Gu_2025_ICCV, author = {Gu, Jiawei and Qiao, Ziyue and Li, Zechao}, title = {Gradient Short-Circuit: Efficient Out-of-Distribution Detection via Feature Intervention}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {457-466} }
CityNav: A Large-Scale Dataset for Real-World Aerial Navigation: Jungdae Lee,

Taiki Miyanishi,

Shuhei Kurita,

Koya Sakamoto,

Daichi Azuma,

Yutaka Matsuo,

Nakamasa Inoue; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2025_ICCV, author = {Lee, Jungdae and Miyanishi, Taiki and Kurita, Shuhei and Sakamoto, Koya and Azuma, Daichi and Matsuo, Yutaka and Inoue, Nakamasa}, title = {CityNav: A Large-Scale Dataset for Real-World Aerial Navigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5912-5922} }
Diffusion Guided Adaptive Augmentation for Generalization in Visual Reinforcement Learning: Jeong Woon Lee,

Hyoseok Hwang; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2025_ICCV, author = {Lee, Jeong Woon and Hwang, Hyoseok}, title = {Diffusion Guided Adaptive Augmentation for Generalization in Visual Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {880-889} }
FedAGC: Federated Continual Learning with Asymmetric Gradient Correction: Chengchao Zhang,

Fanhua Shang,

Hongying Liu,

Liang Wan,

Wei Feng; [pdf]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Chengchao and Shang, Fanhua and Liu, Hongying and Wan, Liang and Feng, Wei}, title = {FedAGC: Federated Continual Learning with Asymmetric Gradient Correction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3841-3850} }
Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypes: Tom Fischer,

Xiaojie Zhang,

Eddy Ilg; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fischer_2025_ICCV, author = {Fischer, Tom and Zhang, Xiaojie and Ilg, Eddy}, title = {Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9790-9800} }
GT-Mean Loss: A Simple Yet Effective Solution for Brightness Mismatch in Low-Light Image Enhancement: Jingxi Liao,

Shijie Hao,

Richang Hong,

Meng Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liao_2025_ICCV, author = {Liao, Jingxi and Hao, Shijie and Hong, Richang and Wang, Meng}, title = {GT-Mean Loss: A Simple Yet Effective Solution for Brightness Mismatch in Low-Light Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6112-6121} }
OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning: Xianhang Li,

Yanqing Liu,

Haoqin Tu,

Cihang Xie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Xianhang and Liu, Yanqing and Tu, Haoqin and Xie, Cihang}, title = {OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3977-3987} }
ViT-EnsembleAttack: Augmenting Ensemble Models for Stronger Adversarial Transferability in Vision Transformers: Hanwen Cao,

Haobo Lu,

Xiaosen Wang,

Kun He; [pdf]
[bibtex]
@InProceedings{Cao_2025_ICCV, author = {Cao, Hanwen and Lu, Haobo and Wang, Xiaosen and He, Kun}, title = {ViT-EnsembleAttack: Augmenting Ensemble Models for Stronger Adversarial Transferability in Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2000-2009} }
VOccl3D: A Video Benchmark Dataset for 3D Human Pose and Shape Estimation under real Occlusions: Yash Garg,

Saketh Bachu,

Arindam Dutta,

Rohit Lal,

Sarosij Bose,

Calvin-Khang Ta,

M. Salman Asif,

Amit Roy-Chowdhury; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Garg_2025_ICCV, author = {Garg, Yash and Bachu, Saketh and Dutta, Arindam and Lal, Rohit and Bose, Sarosij and Ta, Calvin-Khang and Asif, M. Salman and Roy-Chowdhury, Amit}, title = {VOccl3D: A Video Benchmark Dataset for 3D Human Pose and Shape Estimation under real Occlusions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7350-7360} }
PoseAnchor: Robust Root Position Estimation for 3D Human Pose Estimation: Jun-Hee Kim,

Jumin Han,

Seong-Whan Lee; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2025_ICCV, author = {Kim, Jun-Hee and Han, Jumin and Lee, Seong-Whan}, title = {PoseAnchor: Robust Root Position Estimation for 3D Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7079-7088} }
Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization: Kesen Zhao,

Beier Zhu,

Qianru Sun,

Hanwang Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2025_ICCV, author = {Zhao, Kesen and Zhu, Beier and Sun, Qianru and Zhang, Hanwang}, title = {Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2303-2312} }
On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations: Amir Mehrpanah,

Matteo Gamba,

Kevin Smith,

Hossein Azizpour; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mehrpanah_2025_ICCV, author = {Mehrpanah, Amir and Gamba, Matteo and Smith, Kevin and Azizpour, Hossein}, title = {On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3531-3541} }
Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts: Zixuan Hu,

Dongxiao Li,

Xinzhu Ma,

Shixiang Tang,

Xiaotong Li,

Wenhan Yang,

Ling-Yu Duan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hu_2025_ICCV, author = {Hu, Zixuan and Li, Dongxiao and Ma, Xinzhu and Tang, Shixiang and Li, Xiaotong and Yang, Wenhan and Duan, Ling-Yu}, title = {Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7273-7283} }
RayPose: Ray Bundling Diffusion for Template Views in Unseen 6D Object Pose Estimation: Junwen Huang,

Shishir Reddy Vutukur,

Peter KT Yu,

Nassir Navab,

Slobodan Ilic,

Benjamin Busam; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2025_ICCV, author = {Huang, Junwen and Vutukur, Shishir Reddy and Yu, Peter KT and Navab, Nassir and Ilic, Slobodan and Busam, Benjamin}, title = {RayPose: Ray Bundling Diffusion for Template Views in Unseen 6D Object Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9102-9112} }
Integrating Task-Specific and Universal Adapters for Pre-Trained Model-based Class-Incremental Learning: Yan Wang,

Da-Wei Zhou,

Han-Jia Ye; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Yan and Zhou, Da-Wei and Ye, Han-Jia}, title = {Integrating Task-Specific and Universal Adapters for Pre-Trained Model-based Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {806-816} }
TriDi: Trilateral Diffusion of 3D Humans, Objects, and Interactions: Ilya A. Petrov,

Riccardo Marin,

Julian Chibane,

Gerard Pons-Moll; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Petrov_2025_ICCV, author = {Petrov, Ilya A. and Marin, Riccardo and Chibane, Julian and Pons-Moll, Gerard}, title = {TriDi: Trilateral Diffusion of 3D Humans, Objects, and Interactions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5523-5535} }
GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks: Muhammad Danish,

Muhammad Akhtar Munir,

Syed Roshaan Ali Shah,

Kartik Kuckreja,

Fahad Shahbaz Khan,

Paolo Fraccaro,

Alexandre Lacoste,

Salman Khan; [pdf] [supp]
[bibtex]
@InProceedings{Danish_2025_ICCV, author = {Danish, Muhammad and Munir, Muhammad Akhtar and Shah, Syed Roshaan Ali and Kuckreja, Kartik and Khan, Fahad Shahbaz and Fraccaro, Paolo and Lacoste, Alexandre and Khan, Salman}, title = {GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7132-7142} }
High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation: Runyang Feng,

Hyung Jin Chang,

Tze Ho Elden Tse,

Boeun Kim,

Yi Chang,

Yixing Gao; [pdf] [arXiv]
[bibtex]
@InProceedings{Feng_2025_ICCV, author = {Feng, Runyang and Chang, Hyung Jin and Tse, Tze Ho Elden and Kim, Boeun and Chang, Yi and Gao, Yixing}, title = {High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8929-8938} }
SkySense V2: A Unified Foundation Model for Multi-modal Remote Sensing: Yingying Zhang,

Lixiang Ru,

Kang Wu,

Lei Yu,

Lei Liang,

Yansheng Li,

Jingdong Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Yingying and Ru, Lixiang and Wu, Kang and Yu, Lei and Liang, Lei and Li, Yansheng and Chen, Jingdong}, title = {SkySense V2: A Unified Foundation Model for Multi-modal Remote Sensing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9136-9146} }
Intra-view and Inter-view Correlation Guided Multi-view Novel Class Discovery: Xinhang Wan,

Jiyuan Liu,

Qian Qu,

Suyuan Liu,

Chuyu Zhang,

Fangdi Wang,

Xinwang Liu,

En Zhu,

Kunlun He; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wan_2025_ICCV, author = {Wan, Xinhang and Liu, Jiyuan and Qu, Qian and Liu, Suyuan and Zhang, Chuyu and Wang, Fangdi and Liu, Xinwang and Zhu, En and He, Kunlun}, title = {Intra-view and Inter-view Correlation Guided Multi-view Novel Class Discovery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4114-4124} }
Unsupervised Joint Learning of Optical Flow and Intensity with Event Cameras: Shuang Guo,

Friedhelm Hamann,

Guillermo Gallego; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2025_ICCV, author = {Guo, Shuang and Hamann, Friedhelm and Gallego, Guillermo}, title = {Unsupervised Joint Learning of Optical Flow and Intensity with Event Cameras}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7980-7989} }
Towards Comprehensive Lecture Slides Understanding: Large-scale Dataset and Effective Method: Enming Zhang,

Yuzhe Li,

Yuliang Liu,

Yingying Zhu,

Xiang Bai; [pdf]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Enming and Li, Yuzhe and Liu, Yuliang and Zhu, Yingying and Bai, Xiang}, title = {Towards Comprehensive Lecture Slides Understanding: Large-scale Dataset and Effective Method}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4455-4464} }
Hybrid-TTA: Continual Test-time Adaptation via Dynamic Domain Shift Detection: Hyewon Park,

Hyejin Park,

Jueun Ko,

Dongbo Min; [pdf] [supp]
[bibtex]
@InProceedings{Park_2025_ICCV, author = {Park, Hyewon and Park, Hyejin and Ko, Jueun and Min, Dongbo}, title = {Hybrid-TTA: Continual Test-time Adaptation via Dynamic Domain Shift Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2877-2886} }
NavQ: Learning a Q-Model for Foresighted Vision-and-Language Navigation: Peiran Xu,

Xicheng Gong,

Yadong Mu; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2025_ICCV, author = {Xu, Peiran and Gong, Xicheng and Mu, Yadong}, title = {NavQ: Learning a Q-Model for Foresighted Vision-and-Language Navigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6327-6341} }
PartField: Learning 3D Feature Fields for Part Segmentation and Beyond: Minghua Liu,

Mikaela Angelina Uy,

Donglai Xiang,

Hao Su,

Sanja Fidler,

Nicholas Sharp,

Jun Gao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2025_ICCV, author = {Liu, Minghua and Uy, Mikaela Angelina and Xiang, Donglai and Su, Hao and Fidler, Sanja and Sharp, Nicholas and Gao, Jun}, title = {PartField: Learning 3D Feature Fields for Part Segmentation and Beyond}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9704-9715} }
Mitigating Object Hallucinations via Sentence-Level Early Intervention: Shangpin Peng,

Senqiao Yang,

Li Jiang,

Zhuotao Tian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Peng_2025_ICCV, author = {Peng, Shangpin and Yang, Senqiao and Jiang, Li and Tian, Zhuotao}, title = {Mitigating Object Hallucinations via Sentence-Level Early Intervention}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {635-646} }
PhysSplat: Efficient Physics Simulation for 3D Scenes via MLLM-Guided Gaussian Splatting: Haoyu Zhao,

Hao Wang,

Xingyue Zhao,

Hao Fei,

Hongqiu Wang,

Chengjiang Long,

Hua Zou; [pdf] [supp]
[bibtex]
@InProceedings{Zhao_2025_ICCV, author = {Zhao, Haoyu and Wang, Hao and Zhao, Xingyue and Fei, Hao and Wang, Hongqiu and Long, Chengjiang and Zou, Hua}, title = {PhysSplat: Efficient Physics Simulation for 3D Scenes via MLLM-Guided Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5242-5252} }
OrderChain: Towards General Instruct-Tuning for Stimulating the Ordinal Understanding Ability of MLLM: Jinhong Wang,

Shuo Tong,

Jian Liu,

Dongqi Tang,

Weiqiang Wang,

Wentong Li,

Hongxia Xu,

Danny Z. Chen,

Jintai Chen,

Jian Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Jinhong and Tong, Shuo and Liu, Jian and Tang, Dongqi and Wang, Weiqiang and Li, Wentong and Xu, Hongxia and Chen, Danny Z. and Chen, Jintai and Wu, Jian}, title = {OrderChain: Towards General Instruct-Tuning for Stimulating the Ordinal Understanding Ability of MLLM}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3477-3487} }
Benchmarking Multimodal Large Language Models Against Image Corruptions: Xinkuan Qiu,

Meina Kan,

Yongbin Zhou,

Shiguang Shan; [pdf] [supp]
[bibtex]
@InProceedings{Qiu_2025_ICCV, author = {Qiu, Xinkuan and Kan, Meina and Zhou, Yongbin and Shan, Shiguang}, title = {Benchmarking Multimodal Large Language Models Against Image Corruptions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9014-9023} }
DWIM: Towards Tool-aware Visual Reasoning via Discrepancy-aware Workflow Generation & Instruct-Masking Tuning: Fucai Ke,

Vijay Kumar B G,

Xingjian Leng,

Zhixi Cai,

Zaid Khan,

Weiqing Wang,

Pari Delir Haghighi,

Hamid Rezatofighi,

Manmohan Chandraker; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ke_2025_ICCV, author = {Ke, Fucai and G, Vijay Kumar B and Leng, Xingjian and Cai, Zhixi and Khan, Zaid and Wang, Weiqing and Haghighi, Pari Delir and Rezatofighi, Hamid and Chandraker, Manmohan}, title = {DWIM: Towards Tool-aware Visual Reasoning via Discrepancy-aware Workflow Generation \& Instruct-Masking Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3378-3389} }
RoboTrom-Nav: A Unified Framework for Embodied Navigation Integrating Perception, Planning, and Prediction: Yufeng Zhong,

Chengjian Feng,

Feng Yan,

Fanfan Liu,

Liming Zheng,

Lin Ma; [pdf] [supp]
[bibtex]
@InProceedings{Zhong_2025_ICCV, author = {Zhong, Yufeng and Feng, Chengjian and Yan, Feng and Liu, Fanfan and Zheng, Liming and Ma, Lin}, title = {RoboTrom-Nav: A Unified Framework for Embodied Navigation Integrating Perception, Planning, and Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6416-6425} }
ETA: Energy-based Test-time Adaptation for Depth Completion: Younjoon Chung,

Hyoungseob Park,

Patrick Rim,

Xiaoran Zhang,

Jihe He,

Ziyao Zeng,

Safa Cicek,

Byung-Woo Hong,

James S. Duncan,

Alex Wong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chung_2025_ICCV, author = {Chung, Younjoon and Park, Hyoungseob and Rim, Patrick and Zhang, Xiaoran and He, Jihe and Zeng, Ziyao and Cicek, Safa and Hong, Byung-Woo and Duncan, James S. and Wong, Alex}, title = {ETA: Energy-based Test-time Adaptation for Depth Completion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6001-6012} }
Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images: Tianhao Wu,

Chuanxia Zheng,

Frank Guan,

Andrea Vedaldi,

Tat-Jen Cham; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2025_ICCV, author = {Wu, Tianhao and Zheng, Chuanxia and Guan, Frank and Vedaldi, Andrea and Cham, Tat-Jen}, title = {Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9181-9193} }
ConstStyle: Robust Domain Generalization with Unified Style Transformation: Nam Duong Tran,

Nam Nguyen Phuong,

Hieu H. Pham,

Phi Le Nguyen,

My T. Thai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tran_2025_ICCV, author = {Tran, Nam Duong and Phuong, Nam Nguyen and Pham, Hieu H. and Le Nguyen, Phi and Thai, My T.}, title = {ConstStyle: Robust Domain Generalization with Unified Style Transformation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3174-3183} }
Perspective-Aware Teaching: Adapting Knowledge for Heterogeneous Distillation: Jhe-Hao Lin,

Yi Yao,

Chan-Feng Hsu,

Hong-Xia Xie,

Hong-Han Shuai,

Wen-Huang Cheng; [pdf] [supp]
[bibtex]
@InProceedings{Lin_2025_ICCV, author = {Lin, Jhe-Hao and Yao, Yi and Hsu, Chan-Feng and Xie, Hong-Xia and Shuai, Hong-Han and Cheng, Wen-Huang}, title = {Perspective-Aware Teaching: Adapting Knowledge for Heterogeneous Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4178-4187} }
Mitigating Catastrophic Overfitting in Fast Adversarial Training via Label Information Elimination: Chao Pan,

Ke Tang,

Qing Li,

Xin Yao; [pdf] [supp]
[bibtex]
@InProceedings{Pan_2025_ICCV, author = {Pan, Chao and Tang, Ke and Li, Qing and Yao, Xin}, title = {Mitigating Catastrophic Overfitting in Fast Adversarial Training via Label Information Elimination}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2991-3000} }
Pi-GPS: Enhancing Geometry Problem Solving by Unleashing the Power of Diagrammatic Information: Junbo Zhao,

Ting Zhang,

Jiayu Sun,

Mi Tian,

Hua Huang; [pdf] [supp]
[bibtex]
@InProceedings{Zhao_2025_ICCV, author = {Zhao, Junbo and Zhang, Ting and Sun, Jiayu and Tian, Mi and Huang, Hua}, title = {Pi-GPS: Enhancing Geometry Problem Solving by Unleashing the Power of Diagrammatic Information}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1526-1536} }
PRE-Mamba: A 4D State Space Model for Ultra-High-Frequent Event Camera Deraining: Ciyu Ruan,

Ruishan Guo,

Zihang Gong,

Jingao Xu,

Wenhan Yang,

Xinlei Chen; [pdf] [supp]
[bibtex]
@InProceedings{Ruan_2025_ICCV, author = {Ruan, Ciyu and Guo, Ruishan and Gong, Zihang and Xu, Jingao and Yang, Wenhan and Chen, Xinlei}, title = {PRE-Mamba: A 4D State Space Model for Ultra-High-Frequent Event Camera Deraining}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9169-9180} }
Future-Aware Interaction Network For Motion Forecasting: Shijie Li,

Chunyu Liu,

Xun Xu,

Si Yong Yeo,

Xulei Yang; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Shijie and Liu, Chunyu and Xu, Xun and Yeo, Si Yong and Yang, Xulei}, title = {Future-Aware Interaction Network For Motion Forecasting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7505-7515} }
Stochastic Interpolants for Revealing Stylistic Flows across the History of Art: Pingchuan Ma,

Ming Gui,

Johannes Schusterbauer,

Xiaopei Yang,

Olga Grebenkova,

Vincent Tao Hu,

Björn Ommer; [pdf] [supp]
[bibtex]
@InProceedings{Ma_2025_ICCV, author = {Ma, Pingchuan and Gui, Ming and Schusterbauer, Johannes and Yang, Xiaopei and Grebenkova, Olga and Hu, Vincent Tao and Ommer, Bj\"orn}, title = {Stochastic Interpolants for Revealing Stylistic Flows across the History of Art}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5867-5878} }
MeshMamba: State Space Models for Articulated 3D Mesh Generation and Reconstruction: Yusuke Yoshiyasu,

Leyuan Sun,

Ryusuke Sagawa; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yoshiyasu_2025_ICCV, author = {Yoshiyasu, Yusuke and Sun, Leyuan and Sagawa, Ryusuke}, title = {MeshMamba: State Space Models for Articulated 3D Mesh Generation and Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6563-6574} }
Trust but Verify: Programmatic VLM Evaluation in the Wild: Viraj Prabhu,

Senthil Purushwalkam,

An Yan,

Caiming Xiong,

Ran Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Prabhu_2025_ICCV, author = {Prabhu, Viraj and Purushwalkam, Senthil and Yan, An and Xiong, Caiming and Xu, Ran}, title = {Trust but Verify: Programmatic VLM Evaluation in the Wild}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3258-3267} }
MonoSOWA: Scalable Monocular 3D Object Detector Without Human Annotations: Jan Skvrna,

Lukas Neumann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Skvrna_2025_ICCV, author = {Skvrna, Jan and Neumann, Lukas}, title = {MonoSOWA: Scalable Monocular 3D Object Detector Without Human Annotations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7613-7623} }
Measuring the Impact of Rotation Equivariance on Aerial Object Detection: Xiuyu Wu,

Xinhao Wang,

Xiubin Zhu,

Lan Yang,

Jiyuan Liu,

Xingchen Hu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2025_ICCV, author = {Wu, Xiuyu and Wang, Xinhao and Zhu, Xiubin and Yang, Lan and Liu, Jiyuan and Hu, Xingchen}, title = {Measuring the Impact of Rotation Equivariance on Aerial Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7329-7339} }
NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors: Yanrui Bin,

Wenbo Hu,

Haoyuan Wang,

Xinya Chen,

Bing Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bin_2025_ICCV, author = {Bin, Yanrui and Hu, Wenbo and Wang, Haoyuan and Chen, Xinya and Wang, Bing}, title = {NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8330-8339} }
Color Matching Using Hypernetwork-Based Kolmogorov-Arnold Networks: Artem Nikonorov,

Georgy Perevozchikov,

Andrei Korepanov,

Nancy Mehta,

Mahmoud Afifi,

Egor Ershov,

Radu Timofte; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nikonorov_2025_ICCV, author = {Nikonorov, Artem and Perevozchikov, Georgy and Korepanov, Andrei and Mehta, Nancy and Afifi, Mahmoud and Ershov, Egor and Timofte, Radu}, title = {Color Matching Using Hypernetwork-Based Kolmogorov-Arnold Networks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7099-7109} }
MGSfM: Multi-Camera Geometry Driven Global Structure-from-Motion: Peilin Tao,

Hainan Cui,

Diantao Tu,

Shuhan Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tao_2025_ICCV, author = {Tao, Peilin and Cui, Hainan and Tu, Diantao and Shen, Shuhan}, title = {MGSfM: Multi-Camera Geometry Driven Global Structure-from-Motion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5232-5241} }
WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions: Zizhang Li,

Hong-Xing Yu,

Wei Liu,

Yin Yang,

Charles Herrmann,

Gordon Wetzstein,

Jiajun Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Zizhang and Yu, Hong-Xing and Liu, Wei and Yang, Yin and Herrmann, Charles and Wetzstein, Gordon and Wu, Jiajun}, title = {WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9080-9090} }
SRefiner: Soft-Braid Attention for Multi-Agent Trajectory Refinement: Liwen Xiao,

Zhiyu Pan,

Zhicheng Wang,

Zhiguo Cao,

Wei Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiao_2025_ICCV, author = {Xiao, Liwen and Pan, Zhiyu and Wang, Zhicheng and Cao, Zhiguo and Li, Wei}, title = {SRefiner: Soft-Braid Attention for Multi-Agent Trajectory Refinement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {960-969} }
Learning 3D Object Spatial Relationships from Pre-trained 2D Diffusion Models: Sangwon Baik,

Hyeonwoo Kim,

Hanbyul Joo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Baik_2025_ICCV, author = {Baik, Sangwon and Kim, Hyeonwoo and Joo, Hanbyul}, title = {Learning 3D Object Spatial Relationships from Pre-trained 2D Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8418-8428} }
Event-guided Unified Framework for Low-light Video Enhancement, Frame Interpolation, and Deblurring: Taewoo Kim,

Kuk-Jin Yoon; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2025_ICCV, author = {Kim, Taewoo and Yoon, Kuk-Jin}, title = {Event-guided Unified Framework for Low-light Video Enhancement, Frame Interpolation, and Deblurring}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8524-8534} }
Physics Context Builders: A Modular Framework for Physical Reasoning in Vision-Language Models: Vahid Balazadeh,

Mohammadmehdi Ataei,

Hyunmin Cheong,

Amir Hosein Khasahmadi,

Rahul G. Krishnan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Balazadeh_2025_ICCV, author = {Balazadeh, Vahid and Ataei, Mohammadmehdi and Cheong, Hyunmin and Khasahmadi, Amir Hosein and Krishnan, Rahul G.}, title = {Physics Context Builders: A Modular Framework for Physical Reasoning in Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7318-7328} }
Bridging the Sky and Ground: Towards View-Invariant Feature Learning for Aerial-Ground Person Re-Identification: Wajahat Khalid,

Bin Liu,

Xulin Li,

Muhammad Waqas,

Muhammad Sher Afgan; [pdf] [supp]
[bibtex]
@InProceedings{Khalid_2025_ICCV, author = {Khalid, Wajahat and Liu, Bin and Li, Xulin and Waqas, Muhammad and Afgan, Muhammad Sher}, title = {Bridging the Sky and Ground: Towards View-Invariant Feature Learning for Aerial-Ground Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9749-9758} }
Prototype Guided Backdoor Defense via Activation Space Manipulation: Venkat Adithya Amula,

Sunayana Samavedam,

Saurabh Saini,

Avani Gupta,

P J Narayanan; [pdf] [supp]
[bibtex]
@InProceedings{Amula_2025_ICCV, author = {Amula, Venkat Adithya and Samavedam, Sunayana and Saini, Saurabh and Gupta, Avani and Narayanan, P J}, title = {Prototype Guided Backdoor Defense via Activation Space Manipulation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2195-2205} }
Achieving More with Less: Additive Prompt Tuning for Rehearsal-Free Class-Incremental Learning: Haoran Chen,

Ping Wang,

Zihan Zhou,

Xu Zhang,

Zuxuan Wu,

Yu-Gang Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Haoran and Wang, Ping and Zhou, Zihan and Zhang, Xu and Wu, Zuxuan and Jiang, Yu-Gang}, title = {Achieving More with Less: Additive Prompt Tuning for Rehearsal-Free Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {340-349} }
VLRMBench: A Comprehensive and Challenging Benchmark for Vision-Language Reward Models: Jiacheng Ruan,

Wenzhen Yuan,

Xian Gao,

Ye Guo,

Daoxin Zhang,

Zhe Xu,

Yao Hu,

Ting Liu,

Yuzhuo Fu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ruan_2025_ICCV, author = {Ruan, Jiacheng and Yuan, Wenzhen and Gao, Xian and Guo, Ye and Zhang, Daoxin and Xu, Zhe and Hu, Yao and Liu, Ting and Fu, Yuzhuo}, title = {VLRMBench: A Comprehensive and Challenging Benchmark for Vision-Language Reward Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3163-3173} }
SITE: towards Spatial Intelligence Thorough Evaluation: Wenqi Wang,

Reuben Tan,

Pengyue Zhu,

Jianwei Yang,

Zhengyuan Yang,

Lijuan Wang,

Andrey Kolobov,

Jianfeng Gao,

Boqing Gong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Wenqi and Tan, Reuben and Zhu, Pengyue and Yang, Jianwei and Yang, Zhengyuan and Wang, Lijuan and Kolobov, Andrey and Gao, Jianfeng and Gong, Boqing}, title = {SITE: towards Spatial Intelligence Thorough Evaluation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9058-9069} }
FW-Merging: Scaling Model Merging with Frank-Wolfe Optimization: Hao Mark Chen,

Shell Xu Hu,

Wayne Luk,

Timothy Hospedales,

Hongxiang Fan; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Hao Mark and Hu, Shell Xu and Luk, Wayne and Hospedales, Timothy and Fan, Hongxiang}, title = {FW-Merging: Scaling Model Merging with Frank-Wolfe Optimization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3390-3400} }
VOVTrack: Exploring the Potentiality in Raw Videos for Open-Vocabulary Multi-Object Tracking: Zekun Qian,

Ruize Han,

Junhui Hou,

Linqi Song,

Wei Feng; [pdf] [supp]
[bibtex]
@InProceedings{Qian_2025_ICCV, author = {Qian, Zekun and Han, Ruize and Hou, Junhui and Song, Linqi and Feng, Wei}, title = {VOVTrack: Exploring the Potentiality in Raw Videos for Open-Vocabulary Multi-Object Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7472-7482} }
Neural Solver of Dichromatic Reflection Model for Specular Highlight Removal: Gang Fu; [pdf]
[bibtex]
@InProceedings{Fu_2025_ICCV, author = {Fu, Gang}, title = {Neural Solver of Dichromatic Reflection Model for Specular Highlight Removal}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7241-7250} }
Weakly-Supervised Learning of Dense Functional Correspondences: Stefan Stojanov,

Linan Zhao,

Yunzhi Zhang,

Daniel L. K. Yamins,

Jiajun Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Stojanov_2025_ICCV, author = {Stojanov, Stefan and Zhao, Linan and Zhang, Yunzhi and Yamins, Daniel L. K. and Wu, Jiajun}, title = {Weakly-Supervised Learning of Dense Functional Correspondences}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6981-6993} }
SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation: Hao Ban,

Gokul Ram Subramani,

Kaiyi Ji; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ban_2025_ICCV, author = {Ban, Hao and Subramani, Gokul Ram and Ji, Kaiyi}, title = {SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {785-795} }
FastJSMA: Accelerating Jacobian-based Saliency Map Attacks through Gradient Decoupling: Zhenghao Gao,

Shengjie Xu,

Zijing Li,

Meixi Chen,

Chaojian Yu,

Yuanjie Shao,

Changxin Gao; [pdf]
[bibtex]
@InProceedings{Gao_2025_ICCV, author = {Gao, Zhenghao and Xu, Shengjie and Li, Zijing and Chen, Meixi and Yu, Chaojian and Shao, Yuanjie and Gao, Changxin}, title = {FastJSMA: Accelerating Jacobian-based Saliency Map Attacks through Gradient Decoupling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1506-1515} }
TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction: Xuying Zhang,

Yutong Liu,

Yangguang Li,

Renrui Zhang,

Yufei Liu,

Kai Wang,

Wanli Ouyang,

Zhiwei Xiong,

Peng Gao,

Qibin Hou,

Ming-Ming Cheng; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Xuying and Liu, Yutong and Li, Yangguang and Zhang, Renrui and Liu, Yufei and Wang, Kai and Ouyang, Wanli and Xiong, Zhiwei and Gao, Peng and Hou, Qibin and Cheng, Ming-Ming}, title = {TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5134-5145} }
MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation: Pingrui Zhang,

Xianqiang Gao,

Yuhan Wu,

Kehui Liu,

Dong Wang,

Zhigang Wang,

Bin Zhao,

Yan Ding,

Xuelong Li; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Pingrui and Gao, Xianqiang and Wu, Yuhan and Liu, Kehui and Wang, Dong and Wang, Zhigang and Zhao, Bin and Ding, Yan and Li, Xuelong}, title = {MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6315-6326} }
Generalized Deep Multi-view Clustering via Causal Learning with Partially Aligned Cross-view Correspondence: Xihong Yang,

Siwei Wang,

Jiaqi Jin,

Fangdi Wang,

Tianrui Liu,

Yueming Jin,

Xinwang Liu,

En Zhu,

Kunlun He; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Xihong and Wang, Siwei and Jin, Jiaqi and Wang, Fangdi and Liu, Tianrui and Jin, Yueming and Liu, Xinwang and Zhu, En and He, Kunlun}, title = {Generalized Deep Multi-view Clustering via Causal Learning with Partially Aligned Cross-view Correspondence}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1990-1999} }
MeasureXpert: Automatic Anthropometric Measurement Extraction from Two Unregistered, Partial, Posed, and Dressed Body Scans: Ran Zhao,

Xinxin Dai,

Pengpeng Hu,

Vasile Palade,

Adrian Munteanu; [pdf] [supp]
[bibtex]
@InProceedings{Zhao_2025_ICCV, author = {Zhao, Ran and Dai, Xinxin and Hu, Pengpeng and Palade, Vasile and Munteanu, Adrian}, title = {MeasureXpert: Automatic Anthropometric Measurement Extraction from Two Unregistered, Partial, Posed, and Dressed Body Scans}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9605-9615} }
FedMeNF: Privacy-Preserving Federated Meta-Learning for Neural Fields: Junhyeog Yun,

Minui Hong,

Gunhee Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yun_2025_ICCV, author = {Yun, Junhyeog and Hong, Minui and Kim, Gunhee}, title = {FedMeNF: Privacy-Preserving Federated Meta-Learning for Neural Fields}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2161-2171} }
A Hyperdimensional One Place Signature to Represent Them All: Stackable Descriptors For Visual Place Recognition: Connor Malone,

Somayeh Hussaini,

Tobias Fischer,

Michael Milford; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Malone_2025_ICCV, author = {Malone, Connor and Hussaini, Somayeh and Fischer, Tobias and Milford, Michael}, title = {A Hyperdimensional One Place Signature to Represent Them All: Stackable Descriptors For Visual Place Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9822-9833} }
Large Multi-modal Models Can Interpret Features in Large Multi-modal Models: Kaichen Zhang,

Yifei Shen,

Bo Li,

Ziwei Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Kaichen and Shen, Yifei and Li, Bo and Liu, Ziwei}, title = {Large Multi-modal Models Can Interpret Features in Large Multi-modal Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3650-3661} }
Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data and Metric Perspectives: Shaoyuan Xie,

Lingdong Kong,

Yuhao Dong,

Chonghao Sima,

Wenwei Zhang,

Qi Alfred Chen,

Ziwei Liu,

Liang Pan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xie_2025_ICCV, author = {Xie, Shaoyuan and Kong, Lingdong and Dong, Yuhao and Sima, Chonghao and Zhang, Wenwei and Chen, Qi Alfred and Liu, Ziwei and Pan, Liang}, title = {Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data and Metric Perspectives}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6585-6597} }
Deep Incomplete Multi-view Clustering with Distribution Dual-Consistency Recovery Guidance: Jiaqi Jin,

Siwei Wang,

Zhibin Dong,

Xihong Yang,

Xinwang Liu,

En Zhu,

Kunlun He; [pdf] [arXiv]
[bibtex]
@InProceedings{Jin_2025_ICCV, author = {Jin, Jiaqi and Wang, Siwei and Dong, Zhibin and Yang, Xihong and Liu, Xinwang and Zhu, En and He, Kunlun}, title = {Deep Incomplete Multi-view Clustering with Distribution Dual-Consistency Recovery Guidance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1016-1026} }
3D Mesh Editing using Masked LRMs: Will Gao,

Dilin Wang,

Yuchen Fan,

Aljaz Bozic,

Tuur Stuyck,

Zhengqin Li,

Zhao Dong,

Rakesh Ranjan,

Nikolaos Sarafianos; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2025_ICCV, author = {Gao, Will and Wang, Dilin and Fan, Yuchen and Bozic, Aljaz and Stuyck, Tuur and Li, Zhengqin and Dong, Zhao and Ranjan, Rakesh and Sarafianos, Nikolaos}, title = {3D Mesh Editing using Masked LRMs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7154-7165} }
Acknowledging Focus Ambiguity in Visual Questions: Chongyan Chen,

Yu-Yun Tseng,

Zhuoheng Li,

Anush Venkatesh,

Danna Gurari; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Chongyan and Tseng, Yu-Yun and Li, Zhuoheng and Venkatesh, Anush and Gurari, Danna}, title = {Acknowledging Focus Ambiguity in Visual Questions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1228-1238} }
DRaM-LHM: A Quaternion Framework for Iterative Camera Pose Estimation: Chen Lin,

Weizhi Du,

Zhixiang Min,

Baochen She,

Enrique Dunn,

Sonya M. Hanson; [pdf] [supp]
[bibtex]
@InProceedings{Lin_2025_ICCV, author = {Lin, Chen and Du, Weizhi and Min, Zhixiang and She, Baochen and Dunn, Enrique and Hanson, Sonya M.}, title = {DRaM-LHM: A Quaternion Framework for Iterative Camera Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6447-6455} }
Revisiting Image Fusion for Multi-Illuminant White-Balance Correction: David Serrano-Lozano,

Aditya Arora,

Luis Herranz,

Konstantinos G. Derpanis,

Michael S. Brown,

Javier Vazquez-Corral; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Serrano-Lozano_2025_ICCV, author = {Serrano-Lozano, David and Arora, Aditya and Herranz, Luis and Derpanis, Konstantinos G. and Brown, Michael S. and Vazquez-Corral, Javier}, title = {Revisiting Image Fusion for Multi-Illuminant White-Balance Correction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8275-8284} }
Combinative Matching for Geometric Shape Assembly: Nahyuk Lee,

Juhong Min,

Junhong Lee,

Chunghyun Park,

Minsu Cho; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2025_ICCV, author = {Lee, Nahyuk and Min, Juhong and Lee, Junhong and Park, Chunghyun and Cho, Minsu}, title = {Combinative Matching for Geometric Shape Assembly}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9540-9549} }
DAViD: Data-efficient and Accurate Vision Models from Synthetic Data: Fatemeh Saleh,

Sadegh Aliakbarian,

Charlie Hewitt,

Lohit Petikam,

Xian Xiao,

Antonio Criminisi,

Thomas J. Cashman,

Tadas Baltrusaitis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Saleh_2025_ICCV, author = {Saleh, Fatemeh and Aliakbarian, Sadegh and Hewitt, Charlie and Petikam, Lohit and Xiao, Xian and Criminisi, Antonio and Cashman, Thomas J. and Baltrusaitis, Tadas}, title = {DAViD: Data-efficient and Accurate Vision Models from Synthetic Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5348-5358} }
Learning Interpretable Queries for Explainable Image Classification with Information Pursuit: Stefan Kolek,

Aditya Chattopadhyay,

Kwan Ho Ryan Chan,

Hector Andrade-Loarca,

Gitta Kutyniok,

René Vidal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kolek_2025_ICCV, author = {Kolek, Stefan and Chattopadhyay, Aditya and Chan, Kwan Ho Ryan and Andrade-Loarca, Hector and Kutyniok, Gitta and Vidal, Ren\'e}, title = {Learning Interpretable Queries for Explainable Image Classification with Information Pursuit}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3947-3956} }
LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement: Jieming Bian,

Lei Wang,

Letian Zhang,

Jie Xu; [pdf] [supp]
[bibtex]
@InProceedings{Bian_2025_ICCV, author = {Bian, Jieming and Wang, Lei and Zhang, Letian and Xu, Jie}, title = {LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3737-3746} }
AIRA: Activation-Informed Low-Rank Adaptation for Large Models: Lujun Li,

Dezhi Li,

Cheng Lin,

Wei Li,

Wei Xue,

Sirui Han,

Yike Guo; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Lujun and Li, Dezhi and Lin, Cheng and Li, Wei and Xue, Wei and Han, Sirui and Guo, Yike}, title = {AIRA: Activation-Informed Low-Rank Adaptation for Large Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1729-1739} }
4D Visual Pre-training for Robot Learning: Chengkai Hou,

Yanjie Ze,

Yankai Fu,

Zeyu Gao,

Songbo Hu,

Yue Yu,

Shanghang Zhang,

Huazhe Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hou_2025_ICCV, author = {Hou, Chengkai and Ze, Yanjie and Fu, Yankai and Gao, Zeyu and Hu, Songbo and Yu, Yue and Zhang, Shanghang and Xu, Huazhe}, title = {4D Visual Pre-training for Robot Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8451-8461} }
LONG3R: Long Sequence Streaming 3D Reconstruction: Zhuoguang Chen,

Minghui Qin,

Tianyuan Yuan,

Zhe Liu,

Hang Zhao; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Zhuoguang and Qin, Minghui and Yuan, Tianyuan and Liu, Zhe and Zhao, Hang}, title = {LONG3R: Long Sequence Streaming 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5273-5284} }
Sparsity Outperforms Low-Rank Projections in Few-Shot Adaptation: Nairouz Mrabah,

Nicolas Richet,

Ismail Ben Ayed,

Eric Granger; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mrabah_2025_ICCV, author = {Mrabah, Nairouz and Richet, Nicolas and Ben Ayed, Ismail and Granger, Eric}, title = {Sparsity Outperforms Low-Rank Projections in Few-Shot Adaptation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3143-3152} }
Hyper-Depth: Hypergraph-based Multi-Scale Representation Fusion for Monocular Depth Estimation: Lin Bie,

Siqi Li,

Yifan Feng,

Yue Gao; [pdf]
[bibtex]
@InProceedings{Bie_2025_ICCV, author = {Bie, Lin and Li, Siqi and Feng, Yifan and Gao, Yue}, title = {Hyper-Depth: Hypergraph-based Multi-Scale Representation Fusion for Monocular Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5081-5090} }
SMARTIES: Spectrum-Aware Multi-Sensor Auto-Encoder for Remote Sensing Images: Gencer Sumbul,

Chang Xu,

Emanuele Dalsasso,

Devis Tuia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sumbul_2025_ICCV, author = {Sumbul, Gencer and Xu, Chang and Dalsasso, Emanuele and Tuia, Devis}, title = {SMARTIES: Spectrum-Aware Multi-Sensor Auto-Encoder for Remote Sensing Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5569-5578} }
Bootstrapping Grounded Chain-of-Thought in Multimodal LLMs for Data-Efficient Model Adaptation: Jiaer Xia,

Bingkui Tong,

Yuhang Zang,

Rui Shao,

Kaiyang Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xia_2025_ICCV, author = {Xia, Jiaer and Tong, Bingkui and Zang, Yuhang and Shao, Rui and Zhou, Kaiyang}, title = {Bootstrapping Grounded Chain-of-Thought in Multimodal LLMs for Data-Efficient Model Adaptation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {208-217} }
Instruction-Grounded Visual Projectors for Continual Learning of Generative Vision-Language Models: Hyundong Jin,

Hyung Jin Chang,

Eunwoo Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jin_2025_ICCV, author = {Jin, Hyundong and Chang, Hyung Jin and Kim, Eunwoo}, title = {Instruction-Grounded Visual Projectors for Continual Learning of Generative Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3466-3476} }
Proactive Scene Decomposition and Reconstruction: Baicheng Li,

Zike Yan,

Dong Wu,

Hongbin Zha; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Baicheng and Yan, Zike and Wu, Dong and Zha, Hongbin}, title = {Proactive Scene Decomposition and Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9780-9789} }
Estimating 2D Camera Motion with Hybrid Motion Basis: Haipeng Li,

Tianhao Zhou,

Zhanglei Yang,

Yi Wu,

Yan Chen,

Zijing Mao,

Shen Cheng,

Bing Zeng,

Shuaicheng Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Haipeng and Zhou, Tianhao and Yang, Zhanglei and Wu, Yi and Chen, Yan and Mao, Zijing and Cheng, Shen and Zeng, Bing and Liu, Shuaicheng}, title = {Estimating 2D Camera Motion with Hybrid Motion Basis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7624-7633} }
Predict-Optimize-Distill: A Self-Improving Cycle for 4D Object Understanding: Mingxuan Wu,

Huang Huang,

Justin Kerr,

Chung Min Kim,

Anthony Zhang,

Brent Yi,

Angjoo Kanazawa; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2025_ICCV, author = {Wu, Mingxuan and Huang, Huang and Kerr, Justin and Kim, Chung Min and Zhang, Anthony and Yi, Brent and Kanazawa, Angjoo}, title = {Predict-Optimize-Distill: A Self-Improving Cycle for 4D Object Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6575-6584} }
Fine-grained Spatiotemporal Grounding on Egocentric Videos: Shuo Liang,

Yiwu Zhong,

Zi-Yuan Hu,

Yeyao Tao,

Liwei Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liang_2025_ICCV, author = {Liang, Shuo and Zhong, Yiwu and Hu, Zi-Yuan and Tao, Yeyao and Wang, Liwei}, title = {Fine-grained Spatiotemporal Grounding on Egocentric Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9385-9395} }
PlaceIt3D: Language-Guided Object Placement in Real 3D Scenes: Ahmed Abdelreheem,

Filippo Aleotti,

Jamie Watson,

Zawar Qureshi,

Abdelrahman Eldesokey,

Peter Wonka,

Gabriel Brostow,

Sara Vicente,

Guillermo Garcia-Hernando; [pdf] [arXiv]
[bibtex]
@InProceedings{Abdelreheem_2025_ICCV, author = {Abdelreheem, Ahmed and Aleotti, Filippo and Watson, Jamie and Qureshi, Zawar and Eldesokey, Abdelrahman and Wonka, Peter and Brostow, Gabriel and Vicente, Sara and Garcia-Hernando, Guillermo}, title = {PlaceIt3D: Language-Guided Object Placement in Real 3D Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6645-6655} }
TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning: Siqi Luo,

Haoran Yang,

Yi Xin,

Mingyang Yi,

Guangyang Wu,

Guangtao Zhai,

Xiaohong Liu; [pdf]
[bibtex]
@InProceedings{Luo_2025_ICCV, author = {Luo, Siqi and Yang, Haoran and Xin, Yi and Yi, Mingyang and Wu, Guangyang and Zhai, Guangtao and Liu, Xiaohong}, title = {TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4360-4369} }
Staining and Locking Computer Vision Models Without Retraining: Oliver J. Sutton,

Qinghua Zhou,

George Leete,

Alexander N. Gorban,

Ivan Y. Tyukin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sutton_2025_ICCV, author = {Sutton, Oliver J. and Zhou, Qinghua and Leete, George and Gorban, Alexander N. and Tyukin, Ivan Y.}, title = {Staining and Locking Computer Vision Models Without Retraining}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2346-2355} }
Consistent Time-of-Flight Depth Denoising via Graph-Informed Geometric Attention: Weida Wang,

Changyong He,

Jin Zeng,

Di Qiu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Weida and He, Changyong and Zeng, Jin and Qiu, Di}, title = {Consistent Time-of-Flight Depth Denoising via Graph-Informed Geometric Attention}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5188-5197} }
Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?: Yuru Jia,

Valerio Marsocci,

Ziyang Gong,

Xue Yang,

Maarten Vergauwen,

Andrea Nascetti; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jia_2025_ICCV, author = {Jia, Yuru and Marsocci, Valerio and Gong, Ziyang and Yang, Xue and Vergauwen, Maarten and Nascetti, Andrea}, title = {Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8429-8440} }
AJAHR: Amputated Joint Aware 3D Human Mesh Recovery: Hyunjin Cho,

Giyun Choi,

Jongwon Choi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cho_2025_ICCV, author = {Cho, Hyunjin and Choi, Giyun and Choi, Jongwon}, title = {AJAHR: Amputated Joint Aware 3D Human Mesh Recovery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7925-7935} }
Fish2Mesh Transformer: 3D Human Mesh Recovery from Egocentric Vision: Tianma Shen,

Aditya Puranik,

James Vong,

Vrushabh Deogirikar,

Ryan Fell,

Julianna Dietrich,

Maria Kyrarini,

Christopher Kitts,

David C. Jeong; [pdf] [supp]
[bibtex]
@InProceedings{Shen_2025_ICCV, author = {Shen, Tianma and Puranik, Aditya and Vong, James and Deogirikar, Vrushabh and Fell, Ryan and Dietrich, Julianna and Kyrarini, Maria and Kitts, Christopher and Jeong, David C.}, title = {Fish2Mesh Transformer: 3D Human Mesh Recovery from Egocentric Vision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6498-6507} }
Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Model: Shiming Chen,

Bowen Duan,

Salman Khan,

Fahad Shahbaz Khan; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Shiming and Duan, Bowen and Khan, Salman and Khan, Fahad Shahbaz}, title = {Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Model}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {478-487} }
MaGS: Reconstructing and Simulating Dynamic 3D Objects with Mesh-adsorbed Gaussian Splatting: Shaojie Ma,

Yawei Luo,

Wei Yang,

Yi Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2025_ICCV, author = {Ma, Shaojie and Luo, Yawei and Yang, Wei and Yang, Yi}, title = {MaGS: Reconstructing and Simulating Dynamic 3D Objects with Mesh-adsorbed Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8745-8755} }
SceneMI: Motion In-betweening for Modeling Human-Scene Interaction: Inwoo Hwang,

Bing Zhou,

Young Min Kim,

Jian Wang,

Chuan Guo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hwang_2025_ICCV, author = {Hwang, Inwoo and Zhou, Bing and Kim, Young Min and Wang, Jian and Guo, Chuan}, title = {SceneMI: Motion In-betweening for Modeling Human-Scene Interaction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6034-6045} }
SMoLoRA: Exploring and Defying Dual Catastrophic Forgetting in Continual Visual Instruction Tuning: Ziqi Wang,

Chang Che,

Qi Wang,

Yangyang Li,

Zenglin Shi,

Meng Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Ziqi and Che, Chang and Wang, Qi and Li, Yangyang and Shi, Zenglin and Wang, Meng}, title = {SMoLoRA: Exploring and Defying Dual Catastrophic Forgetting in Continual Visual Instruction Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {177-186} }
DeGauss: Dynamic-Static Decomposition with Gaussian Splatting for Distractor-free 3D Reconstruction: Rui Wang,

Quentin Lohmeyer,

Mirko Meboldt,

Siyu Tang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Rui and Lohmeyer, Quentin and Meboldt, Mirko and Tang, Siyu}, title = {DeGauss: Dynamic-Static Decomposition with Gaussian Splatting for Distractor-free 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6294-6303} }
Time-Aware Auto White Balance in Mobile Photography: Mahmoud Afifi,

Luxi Zhao,

Abhijith Punnappurath,

Mohamed A. Abdelsalam,

Ran Zhang,

Michael S. Brown; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Afifi_2025_ICCV, author = {Afifi, Mahmoud and Zhao, Luxi and Punnappurath, Abhijith and Abdelsalam, Mohamed A. and Zhang, Ran and Brown, Michael S.}, title = {Time-Aware Auto White Balance in Mobile Photography}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5038-5047} }
InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes: Zesong Yang,

Bangbang Yang,

Wenqi Dong,

Chenxuan Cao,

Liyuan Cui,

Yuewen Ma,

Zhaopeng Cui,

Hujun Bao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Zesong and Yang, Bangbang and Dong, Wenqi and Cao, Chenxuan and Cui, Liyuan and Ma, Yuewen and Cui, Zhaopeng and Bao, Hujun}, title = {InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7771-7781} }
Improved Noise Schedule for Diffusion Training: Tiankai Hang,

Shuyang Gu,

Jianmin Bao,

Fangyun Wei,

Dong Chen,

Xin Geng,

Baining Guo; [pdf] [supp]
[bibtex]
@InProceedings{Hang_2025_ICCV, author = {Hang, Tiankai and Gu, Shuyang and Bao, Jianmin and Wei, Fangyun and Chen, Dong and Geng, Xin and Guo, Baining}, title = {Improved Noise Schedule for Diffusion Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4796-4806} }
Information Density Principle for MLLM Benchmarks: Chunyi Li,

Xiaozhe Li,

Zicheng Zhang,

Yuan Tian,

Ziheng Jia,

Xiaohong Liu,

Xiongkuo Min,

Jia Wang,

Haodong Duan,

Kai Chen,

Guangtao Zhai; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Chunyi and Li, Xiaozhe and Zhang, Zicheng and Tian, Yuan and Jia, Ziheng and Liu, Xiaohong and Min, Xiongkuo and Wang, Jia and Duan, Haodong and Chen, Kai and Zhai, Guangtao}, title = {Information Density Principle for MLLM Benchmarks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4167-4177} }
Knowledge-Guided Part Segmentation: Xuejian Gou,

Fang Liu,

Licheng Jiao,

Shuo Li,

Lingling Li,

Hao Wang,

Xu Liu,

Puhua Chen,

Wenping Ma; [pdf] [supp]
[bibtex]
@InProceedings{Gou_2025_ICCV, author = {Gou, Xuejian and Liu, Fang and Jiao, Licheng and Li, Shuo and Li, Lingling and Wang, Hao and Liu, Xu and Chen, Puhua and Ma, Wenping}, title = {Knowledge-Guided Part Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5490-5500} }
Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts: Hongcheng Gao,

Tianyu Pang,

Chao Du,

Taihang Hu,

Zhijie Deng,

Min Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2025_ICCV, author = {Gao, Hongcheng and Pang, Tianyu and Du, Chao and Hu, Taihang and Deng, Zhijie and Lin, Min}, title = {Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2131-2141} }
IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation: Wenxuan Guo,

Xiuwei Xu,

Hang Yin,

Ziwei Wang,

Jianjiang Feng,

Jie Zhou,

Jiwen Lu; [pdf] [supp]
[bibtex]
@InProceedings{Guo_2025_ICCV, author = {Guo, Wenxuan and Xu, Xiuwei and Yin, Hang and Wang, Ziwei and Feng, Jianjiang and Zhou, Jie and Lu, Jiwen}, title = {IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6808-6817} }
EA-KD: Entropy-based Adaptive Knowledge Distillation: Chi-Ping Su,

Ching-Hsun Tseng,

Bin Pu,

Lei Zhao,

Jiewen Yang,

Zhuangzhuang Chen,

Shin-Jye Lee; [pdf] [supp]
[bibtex]
@InProceedings{Su_2025_ICCV, author = {Su, Chi-Ping and Tseng, Ching-Hsun and Pu, Bin and Zhao, Lei and Yang, Jiewen and Chen, Zhuangzhuang and Lee, Shin-Jye}, title = {EA-KD: Entropy-based Adaptive Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {731-740} }
Background Invariance Testing According to Semantic Proximity: Zukang Liao,

Min Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liao_2025_ICCV, author = {Liao, Zukang and Chen, Min}, title = {Background Invariance Testing According to Semantic Proximity}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8056-8065} }
Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learning: Wooseong Jeong,

Kuk-Jin Yoon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jeong_2025_ICCV, author = {Jeong, Wooseong and Yoon, Kuk-Jin}, title = {Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2887-2897} }
ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads: Yifan Li,

Xin Li,

Tianqin Li,

Wenbin He,

Yu Kong,

Liu Ren; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Yifan and Li, Xin and Li, Tianqin and He, Wenbin and Kong, Yu and Ren, Liu}, title = {ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1979-1989} }
BUFFER-X: Towards Zero-Shot Point Cloud Registration in Diverse Scenes: Minkyun Seo,

Hyungtae Lim,

Kanghee Lee,

Luca Carlone,

Jaesik Park; [pdf] [supp]
[bibtex]
@InProceedings{Seo_2025_ICCV, author = {Seo, Minkyun and Lim, Hyungtae and Lee, Kanghee and Carlone, Luca and Park, Jaesik}, title = {BUFFER-X: Towards Zero-Shot Point Cloud Registration in Diverse Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3851-3862} }
VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow: Ada Görgün,

Bernt Schiele,

Jonas Fischer; [pdf] [supp]
[bibtex]
@InProceedings{Gorgun_2025_ICCV, author = {G\"org\"un, Ada and Schiele, Bernt and Fischer, Jonas}, title = {VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4403-4412} }
DisCoPatch: Taming Adversarially-driven Batch Statistics for Improved Out-of-Distribution Detection: Francisco Caetano,

Christiaan Viviers,

Luis A. Zavala-Mondragón,

Peter H.N. De With,

Fons van der Sommen; [pdf] [supp]
[bibtex]
@InProceedings{Caetano_2025_ICCV, author = {Caetano, Francisco and Viviers, Christiaan and Zavala-Mondrag\'on, Luis A. and De With, Peter H.N. and van der Sommen, Fons}, title = {DisCoPatch: Taming Adversarially-driven Batch Statistics for Improved Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2898-2908} }
One Look is Enough: Seamless Patchwise Refinement for Zero-Shot Monocular Depth Estimation on High-Resolution Images: Byeongjun Kwon,

Munchurl Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kwon_2025_ICCV, author = {Kwon, Byeongjun and Kim, Munchurl}, title = {One Look is Enough: Seamless Patchwise Refinement for Zero-Shot Monocular Depth Estimation on High-Resolution Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8077-8087} }
CleanPose: Category-Level Object Pose Estimation via Causal Learning and Knowledge Distillation: Xiao Lin,

Yun Peng,

Liuyi Wang,

Xianyou Zhong,

Minghao Zhu,

Yi Feng,

Jingwei Yang,

Chengju Liu,

Qijun Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2025_ICCV, author = {Lin, Xiao and Peng, Yun and Wang, Liuyi and Zhong, Xianyou and Zhu, Minghao and Feng, Yi and Yang, Jingwei and Liu, Chengju and Chen, Qijun}, title = {CleanPose: Category-Level Object Pose Estimation via Causal Learning and Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5990-6000} }
Lark: Low-Rank Updates After Knowledge Localization for Few-shot Class-Incremental Learning: Jinxin Shi,

Jiabao Zhao,

Yifan Yang,

Xingjiao Wu,

Jiawen Li,

Liang He; [pdf] [supp]
[bibtex]
@InProceedings{Shi_2025_ICCV, author = {Shi, Jinxin and Zhao, Jiabao and Yang, Yifan and Wu, Xingjiao and Li, Jiawen and He, Liang}, title = {Lark: Low-Rank Updates After Knowledge Localization for Few-shot Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3607-3617} }
Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description: Anna-Maria Halacheva,

Yang Miao,

Jan-Nico Zaech,

Xi Wang,

Luc Van Gool,

Danda Pani Paudel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Halacheva_2025_ICCV, author = {Halacheva, Anna-Maria and Miao, Yang and Zaech, Jan-Nico and Wang, Xi and Van Gool, Luc and Paudel, Danda Pani}, title = {Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5633-5644} }
MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics: Bowei Guo,

Shengkun Tang,

Cong Zeng,

Zhiqiang Shen; [pdf] [supp]
[bibtex]
@InProceedings{Guo_2025_ICCV, author = {Guo, Bowei and Tang, Shengkun and Zeng, Cong and Shen, Zhiqiang}, title = {MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1655-1664} }
Not Only Vision: Evolve Visual Speech Recognition via Peripheral Information: Zhaoxin Yuan,

Shuang Yang,

Shiguang Shan,

Xilin Chen; [pdf] [supp]
[bibtex]
@InProceedings{Yuan_2025_ICCV, author = {Yuan, Zhaoxin and Yang, Shuang and Shan, Shiguang and Chen, Xilin}, title = {Not Only Vision: Evolve Visual Speech Recognition via Peripheral Information}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3091-3100} }
CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector: Abhinav Kumar,

Yuliang Guo,

Zhihao Zhang,

Xinyu Huang,

Liu Ren,

Xiaoming Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kumar_2025_ICCV, author = {Kumar, Abhinav and Guo, Yuliang and Zhang, Zhihao and Huang, Xinyu and Ren, Liu and Liu, Xiaoming}, title = {CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8777-8788} }
TimeFormer: Capturing Temporal Relationships of Deformable 3D Gaussians for Robust Reconstruction: Dadong Jiang,

Zhi Hou,

Zhihui Ke,

Xianghui Yang,

Xiaobo Zhou,

Tie Qiu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2025_ICCV, author = {Jiang, Dadong and Hou, Zhi and Ke, Zhihui and Yang, Xianghui and Zhou, Xiaobo and Qiu, Tie}, title = {TimeFormer: Capturing Temporal Relationships of Deformable 3D Gaussians for Robust Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8721-8732} }
Geminio: Language-Guided Gradient Inversion Attacks in Federated Learning: Junjie Shan,

Ziqi Zhao,

Jialin Lu,

Rui Zhang,

Siu Ming Yiu,

Ka-Ho Chow; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shan_2025_ICCV, author = {Shan, Junjie and Zhao, Ziqi and Lu, Jialin and Zhang, Rui and Yiu, Siu Ming and Chow, Ka-Ho}, title = {Geminio: Language-Guided Gradient Inversion Attacks in Federated Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2718-2727} }
Training-free Generation of Temporally Consistent Rewards from VLMs: Yinuo Zhao,

Jiale Yuan,

Zhiyuan Xu,

Xiaoshuai Hao,

Xinyi Zhang,

Kun Wu,

Zhengping Che,

Chi Harold Liu,

Jian Tang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2025_ICCV, author = {Zhao, Yinuo and Yuan, Jiale and Xu, Zhiyuan and Hao, Xiaoshuai and Zhang, Xinyi and Wu, Kun and Che, Zhengping and Liu, Chi Harold and Tang, Jian}, title = {Training-free Generation of Temporally Consistent Rewards from VLMs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8133-8143} }
Breaking Rectangular Shackles: Cross-View Object Segmentation for Fine-Grained Object Geo-Localization: Qingwang Zhang,

Yingying Zhu; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Qingwang and Zhu, Yingying}, title = {Breaking Rectangular Shackles: Cross-View Object Segmentation for Fine-Grained Object Geo-Localization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8197-8206} }
GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs: Xinli Xu,

Wenhang Ge,

Dicong Qiu,

ZhiFei Chen,

Dongyu Yan,

Zhuoyun Liu,

Haoyu Zhao,

Hanfeng Zhao,

Shunsi Zhang,

Junwei Liang,

Ying-Cong Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2025_ICCV, author = {Xu, Xinli and Ge, Wenhang and Qiu, Dicong and Chen, ZhiFei and Yan, Dongyu and Liu, Zhuoyun and Zhao, Haoyu and Zhao, Hanfeng and Zhang, Shunsi and Liang, Junwei and Chen, Ying-Cong}, title = {GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7231-7240} }
Controlling Multimodal LLMs via Reward-guided Decoding: Oscar Mañas,

Pierluca D'Oro,

Koustuv Sinha,

Adriana Romero-Soriano,

Michal Drozdzal,

Aishwarya Agrawal; [pdf] [supp]
[bibtex]
@InProceedings{Manas_2025_ICCV, author = {Ma\~nas, Oscar and D'Oro, Pierluca and Sinha, Koustuv and Romero-Soriano, Adriana and Drozdzal, Michal and Agrawal, Aishwarya}, title = {Controlling Multimodal LLMs via Reward-guided Decoding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1391-1401} }
Auto-Regressively Generating Multi-View Consistent Images: JiaKui Hu,

Yuxiao Yang,

Jialun Liu,

Jinbo Wu,

Chen Zhao,

Yanye Lu; [pdf] [arXiv]
[bibtex]
@InProceedings{Hu_2025_ICCV, author = {Hu, JiaKui and Yang, Yuxiao and Liu, Jialun and Wu, Jinbo and Zhao, Chen and Lu, Yanye}, title = {Auto-Regressively Generating Multi-View Consistent Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2556-2566} }
AIM: Amending Inherent Interpretability via Self-Supervised Masking: Eyad Alshami,

Shashank Agnihotri,

Bernt Schiele,

Margret Keuper; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Alshami_2025_ICCV, author = {Alshami, Eyad and Agnihotri, Shashank and Schiele, Bernt and Keuper, Margret}, title = {AIM: Amending Inherent Interpretability via Self-Supervised Masking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {993-1003} }
I Am Big, You Are Little; I Am Right, You Are Wrong: David A. Kelly,

Akchunya Chanchal,

Nathan Blake; [pdf] [arXiv]
[bibtex]
@InProceedings{Kelly_2025_ICCV, author = {Kelly, David A. and Chanchal, Akchunya and Blake, Nathan}, title = {I Am Big, You Are Little; I Am Right, You Are Wrong}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {817-826} }
Jigsaw++: Imagining Complete Shape Priors for Object Reassembly: Jiaxin Lu,

Gang Hua,

Qixing Huang; [pdf] [supp]
[bibtex]
@InProceedings{Lu_2025_ICCV, author = {Lu, Jiaxin and Hua, Gang and Huang, Qixing}, title = {Jigsaw++: Imagining Complete Shape Priors for Object Reassembly}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6704-6714} }
A Unified Interpretation of Training-Time Out-of-Distribution Detection: Xu Cheng,

Xin Jiang,

Zechao Li; [pdf] [supp]
[bibtex]
@InProceedings{Cheng_2025_ICCV, author = {Cheng, Xu and Jiang, Xin and Li, Zechao}, title = {A Unified Interpretation of Training-Time Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2142-2151} }
Soft Separation and Distillation: Toward Global Uniformity in Federated Unsupervised Learning: Hung-Chieh Fang,

Hsuan-Tien Lin,

Irwin King,

Yifei Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Fang_2025_ICCV, author = {Fang, Hung-Chieh and Lin, Hsuan-Tien and King, Irwin and Zhang, Yifei}, title = {Soft Separation and Distillation: Toward Global Uniformity in Federated Unsupervised Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2971-2980} }
TaxaDiffusion: Progressively Trained Diffusion Model for Fine-Grained Species Generation: Amin Karimi Monsefi,

Mridul Khurana,

Rajiv Ramnath,

Anuj Karpatne,

Wei-Lun Chao,

Cheng Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Monsefi_2025_ICCV, author = {Monsefi, Amin Karimi and Khurana, Mridul and Ramnath, Rajiv and Karpatne, Anuj and Chao, Wei-Lun and Zhang, Cheng}, title = {TaxaDiffusion: Progressively Trained Diffusion Model for Fine-Grained Species Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8579-8589} }
MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation: Vladislav Bargatin,

Egor Chistov,

Alexander Yakovenko,

Dmitriy Vatolin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bargatin_2025_ICCV, author = {Bargatin, Vladislav and Chistov, Egor and Yakovenko, Alexander and Vatolin, Dmitriy}, title = {MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8187-8196} }
Visual Modality Prompt for Adapting Vision-Language Object Detectors: Heitor R. Medeiros,

Atif Belal,

Srikanth Muralidharan,

Eric Granger,

Marco Pedersoli; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Medeiros_2025_ICCV, author = {Medeiros, Heitor R. and Belal, Atif and Muralidharan, Srikanth and Granger, Eric and Pedersoli, Marco}, title = {Visual Modality Prompt for Adapting Vision-Language Object Detectors}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2172-2182} }
Spatial Preference Rewarding for MLLMs Spatial Understanding: Han Qiu,

Peng Gao,

Lewei Lu,

Xiaoqin Zhang,

Ling Shao,

Shijian Lu; [pdf] [supp]
[bibtex]
@InProceedings{Qiu_2025_ICCV, author = {Qiu, Han and Gao, Peng and Lu, Lewei and Zhang, Xiaoqin and Shao, Ling and Lu, Shijian}, title = {Spatial Preference Rewarding for MLLMs Spatial Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {720-730} }
Correspondence as Video: Test-Time Adaption on SAM2 for Reference Segmentation in the Wild: Haoran Wang,

Zekun Li,

Jian Zhang,

Lei Qi,

Yinghuan Shi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Haoran and Li, Zekun and Zhang, Jian and Qi, Lei and Shi, Yinghuan}, title = {Correspondence as Video: Test-Time Adaption on SAM2 for Reference Segmentation in the Wild}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8177-8186} }
WalkVLM: Aid Visually Impaired People Walking by Vision Language Model: Zhiqiang Yuan,

Ting Zhang,

Yeshuang Zhu,

Jiapei Zhang,

Ying Deng,

Zexi Jia,

Peixiang Luo,

Xiaoyue Duan,

Jie Zhou,

Jinchao Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yuan_2025_ICCV, author = {Yuan, Zhiqiang and Zhang, Ting and Zhu, Yeshuang and Zhang, Jiapei and Deng, Ying and Jia, Zexi and Luo, Peixiang and Duan, Xiaoyue and Zhou, Jie and Zhang, Jinchao}, title = {WalkVLM: Aid Visually Impaired People Walking by Vision Language Model}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9845-9854} }
WildSeg3D: Segment Any 3D Objects in the Wild from 2D Images: Yansong Guo,

Jie Hu,

Yansong Qu,

Liujuan Cao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2025_ICCV, author = {Guo, Yansong and Hu, Jie and Qu, Yansong and Cao, Liujuan}, title = {WildSeg3D: Segment Any 3D Objects in the Wild from 2D Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5166-5176} }
CAPTURE: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting: Atin Pothiraj,

Elias Stengel-Eskin,

Jaemin Cho,

Mohit Bansal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pothiraj_2025_ICCV, author = {Pothiraj, Atin and Stengel-Eskin, Elias and Cho, Jaemin and Bansal, Mohit}, title = {CAPTURE: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8001-8010} }
PersPose: 3D Human Pose Estimation with Perspective Encoding and Perspective Rotation: Xiaoyang Hao,

Han Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Hao_2025_ICCV, author = {Hao, Xiaoyang and Li, Han}, title = {PersPose: 3D Human Pose Estimation with Perspective Encoding and Perspective Rotation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8110-8119} }
Scaling Omni-modal Pretraining with Multimodal Context: Advancing Universal Representation Learning Across Modalities: Yiyuan Zhang,

Handong Li,

Jing Liu,

Xiangyu Yue; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Yiyuan and Li, Handong and Liu, Jing and Yue, Xiangyu}, title = {Scaling Omni-modal Pretraining with Multimodal Context: Advancing Universal Representation Learning Across Modalities}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1336-1348} }
ALOcc: Adaptive Lifting-Based 3D Semantic Occupancy and Cost Volume-Based Flow Predictions: Dubing Chen,

Jin Fang,

Wencheng Han,

Xinjing Cheng,

Junbo Yin,

Chengzhong Xu,

Fahad Shahbaz Khan,

Jianbing Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Dubing and Fang, Jin and Han, Wencheng and Cheng, Xinjing and Yin, Junbo and Xu, Chengzhong and Khan, Fahad Shahbaz and Shen, Jianbing}, title = {ALOcc: Adaptive Lifting-Based 3D Semantic Occupancy and Cost Volume-Based Flow Predictions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4156-4166} }
Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models: Teng Ma,

Xiaojun Jia,

Ranjie Duan,

Xinfeng Li,

Yihao Huang,

Xiaoshuang Jia,

Zhixuan Chu,

Wenqi Ren; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2025_ICCV, author = {Ma, Teng and Jia, Xiaojun and Duan, Ranjie and Li, Xinfeng and Huang, Yihao and Jia, Xiaoshuang and Chu, Zhixuan and Ren, Wenqi}, title = {Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2686-2696} }
Boundary Probing for Input Privacy Protection When Using LMM Services: Xiaofei Hui,

Haoxuan Qu,

Ping Hu,

Hossein Rahmani,

Jun Liu; [pdf] [supp]
[bibtex]
@InProceedings{Hui_2025_ICCV, author = {Hui, Xiaofei and Qu, Haoxuan and Hu, Ping and Rahmani, Hossein and Liu, Jun}, title = {Boundary Probing for Input Privacy Protection When Using LMM Services}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {467-477} }
Knowledge Distillation with Refined Logits: Wujie Sun,

Defang Chen,

Siwei Lyu,

Genlang Chen,

Chun Chen,

Can Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2025_ICCV, author = {Sun, Wujie and Chen, Defang and Lyu, Siwei and Chen, Genlang and Chen, Chun and Wang, Can}, title = {Knowledge Distillation with Refined Logits}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1110-1119} }
Tracking Tiny Drones against Clutter: Large-Scale Infrared Benchmark with Motion-Centric Adaptive Algorithm: Jiahao Zhang,

Zongli Jiang,

Jinli Zhang,

Yixin Wei,

Liang Li,

Yizheng Wang,

Gang Wang; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Jiahao and Jiang, Zongli and Zhang, Jinli and Wei, Yixin and Li, Liang and Wang, Yizheng and Wang, Gang}, title = {Tracking Tiny Drones against Clutter: Large-Scale Infrared Benchmark with Motion-Centric Adaptive Algorithm}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7361-7371} }
Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features: Chancharik Mitra,

Brandon Huang,

Tianning Chai,

Zhiqiu Lin,

Assaf Arbelle,

Rogerio Feris,

Leonid Karlinsky,

Trevor Darrell,

Deva Ramanan,

Roei Herzig; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mitra_2025_ICCV, author = {Mitra, Chancharik and Huang, Brandon and Chai, Tianning and Lin, Zhiqiu and Arbelle, Assaf and Feris, Rogerio and Karlinsky, Leonid and Darrell, Trevor and Ramanan, Deva and Herzig, Roei}, title = {Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2760-2772} }
Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection: Jinglun Li,

Kaixun Jiang,

Zhaoyu Chen,

Bo Lin,

Yao Tang,

Weifeng Ge,

Wenqiang Zhang; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Jinglun and Jiang, Kaixun and Chen, Zhaoyu and Lin, Bo and Tang, Yao and Ge, Weifeng and Zhang, Wenqiang}, title = {Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4496-4506} }
EDFFDNet: Towards Accurate and Efficient Unsupervised Multi-Grid Image Registration: Haokai Zhu,

Bo Qu,

Si-Yuan Cao,

Runmin Zhang,

Shujie Chen,

Bailin Yang,

Hui-Liang Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2025_ICCV, author = {Zhu, Haokai and Qu, Bo and Cao, Si-Yuan and Zhang, Runmin and Chen, Shujie and Yang, Bailin and Shen, Hui-Liang}, title = {EDFFDNet: Towards Accurate and Efficient Unsupervised Multi-Grid Image Registration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5102-5111} }
Adaptive Prompt Learning via Gaussian Outlier Synthesis for Out-of-distribution Detection: Yongkang Zhang,

Dongyu She,

Zhong Zhou; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Yongkang and She, Dongyu and Zhou, Zhong}, title = {Adaptive Prompt Learning via Gaussian Outlier Synthesis for Out-of-distribution Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3235-3244} }
ArgoTweak: Towards Self-Updating HD Maps through Structured Priors: Lena Wild,

Rafael Valencia,

Patric Jensfelt; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wild_2025_ICCV, author = {Wild, Lena and Valencia, Rafael and Jensfelt, Patric}, title = {ArgoTweak: Towards Self-Updating HD Maps through Structured Priors}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6091-6100} }
Robust Dataset Condensation using Supervised Contrastive Learning: Nicole Hee-Yeon Kim,

Hwanjun Song; [pdf] [supp]
[bibtex]
@InProceedings{Kim_2025_ICCV, author = {Kim, Nicole Hee-Yeon and Song, Hwanjun}, title = {Robust Dataset Condensation using Supervised Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2857-2866} }
VisNumBench: Evaluating Number Sense of Multimodal Large Language Models: Tengjin Weng,

Jingyi Wang,

Wenhao Jiang,

Zhong Ming; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Weng_2025_ICCV, author = {Weng, Tengjin and Wang, Jingyi and Jiang, Wenhao and Ming, Zhong}, title = {VisNumBench: Evaluating Number Sense of Multimodal Large Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3830-3840} }
Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design: Yuhao Sun,

Yihua Zhang,

Gaowen Liu,

Hongtao Xie,

Sijia Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2025_ICCV, author = {Sun, Yuhao and Zhang, Yihua and Liu, Gaowen and Xie, Hongtao and Liu, Sijia}, title = {Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2417-2428} }
ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers: Qianhao Yuan,

Qingyu Zhang,

Yanjiang Liu,

Jiawei Chen,

Yaojie Lu,

Hongyu Lin,

Jia Zheng,

Xianpei Han,

Le Sun; [pdf] [arXiv]
[bibtex]
@InProceedings{Yuan_2025_ICCV, author = {Yuan, Qianhao and Zhang, Qingyu and Liu, Yanjiang and Chen, Jiawei and Lu, Yaojie and Lin, Hongyu and Zheng, Jia and Han, Xianpei and Sun, Le}, title = {ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {329-339} }
SpikeDiff: Zero-shot High-Quality Video Reconstruction from Chromatic Spike Camera and Sub-millisecond Spike Streams: Siqi Yang,

Jinxiu Liang,

Zhaojun Huang,

Yeliduosi Xiaokaiti,

Yakun Chang,

Zhaofei Yu,

Boxin Shi; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Siqi and Liang, Jinxiu and Huang, Zhaojun and Xiaokaiti, Yeliduosi and Chang, Yakun and Yu, Zhaofei and Shi, Boxin}, title = {SpikeDiff: Zero-shot High-Quality Video Reconstruction from Chromatic Spike Camera and Sub-millisecond Spike Streams}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7905-7914} }
Selective Contrastive Learning for Weakly Supervised Affordance Grounding: WonJun Moon,

Hyun Seok Seong,

Jae-Pil Heo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Moon_2025_ICCV, author = {Moon, WonJun and Seong, Hyun Seok and Heo, Jae-Pil}, title = {Selective Contrastive Learning for Weakly Supervised Affordance Grounding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5210-5220} }
Single-Scanline Relative Pose Estimation for Rolling Shutter Cameras: Petr Hruby,

Marc Pollefeys; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hruby_2025_ICCV, author = {Hruby, Petr and Pollefeys, Marc}, title = {Single-Scanline Relative Pose Estimation for Rolling Shutter Cameras}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7143-7153} }
Real3D: Towards Scaling Large Reconstruction Models with Real Images: Hanwen Jiang,

Qixing Huang,

Georgios Pavlakos; [pdf] [supp]
[bibtex]
@InProceedings{Jiang_2025_ICCV, author = {Jiang, Hanwen and Huang, Qixing and Pavlakos, Georgios}, title = {Real3D: Towards Scaling Large Reconstruction Models with Real Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5821-5833} }
FA: Forced Prompt Learning of Vision-Language Models for Out-of-Distribution Detection: Xinhua Lu,

Runhe Lai,

Yanqi Wu,

Kanghao Chen,

Wei-Shi Zheng,

Ruixuan Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2025_ICCV, author = {Lu, Xinhua and Lai, Runhe and Wu, Yanqi and Chen, Kanghao and Zheng, Wei-Shi and Wang, Ruixuan}, title = {FA: Forced Prompt Learning of Vision-Language Models for Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1152-1161} }
OV-SCAN: Semantically Consistent Alignment for Novel Object Discovery in Open-Vocabulary 3D Object Detection: Adrian Chow,

Evelien Riddell,

Yimu Wang,

Sean Sedwards,

Krzysztof Czarnecki; [pdf] [supp]
[bibtex]
@InProceedings{Chow_2025_ICCV, author = {Chow, Adrian and Riddell, Evelien and Wang, Yimu and Sedwards, Sean and Czarnecki, Krzysztof}, title = {OV-SCAN: Semantically Consistent Alignment for Novel Object Discovery in Open-Vocabulary 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7990-8000} }
The Inter-Intra Modal Measure: A Predictive Lens on Fine-Tuning Outcomes in Vision-Language Models: Laura Niss,

Kevin Vogt-Lowell,

Theodoros Tsiligkaridis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Niss_2025_ICCV, author = {Niss, Laura and Vogt-Lowell, Kevin and Tsiligkaridis, Theodoros}, title = {The Inter-Intra Modal Measure: A Predictive Lens on Fine-Tuning Outcomes in Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2396-2406} }
Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting: Xingyu Miao,

Haoran Duan,

Quanhao Qian,

Jiuniu Wang,

Yang Long,

Ling Shao,

Deli Zhao,

Ran Xu,

Gongjie Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Miao_2025_ICCV, author = {Miao, Xingyu and Duan, Haoran and Qian, Quanhao and Wang, Jiuniu and Long, Yang and Shao, Ling and Zhao, Deli and Xu, Ran and Zhang, Gongjie}, title = {Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {945-959} }
ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning: Xiefan Guo,

Miaomiao Cui,

Liefeng Bo,

Di Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2025_ICCV, author = {Guo, Xiefan and Cui, Miaomiao and Bo, Liefeng and Huang, Di}, title = {ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {678-687} }
IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves: Ruofan Wang,

Juncheng Li,

Yixu Wang,

Bo Wang,

Xiaosen Wang,

Yan Teng,

Yingchun Wang,

Xingjun Ma,

Yu-Gang Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Ruofan and Li, Juncheng and Wang, Yixu and Wang, Bo and Wang, Xiaosen and Teng, Yan and Wang, Yingchun and Ma, Xingjun and Jiang, Yu-Gang}, title = {IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8875-8884} }
UIPro: Unleashing Superior Interaction Capability For GUI Agents: Hongxin Li,

Jingran Su,

Jingfan Chen,

Zheng Ju,

Yuntao Chen,

Qing Li,

Zhaoxiang Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Hongxin and Su, Jingran and Chen, Jingfan and Ju, Zheng and Chen, Yuntao and Li, Qing and Zhang, Zhaoxiang}, title = {UIPro: Unleashing Superior Interaction Capability For GUI Agents}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1613-1623} }
Class-Wise Federated Averaging for Efficient Personalization: Gyuejeong Lee,

Daeyoung Choi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2025_ICCV, author = {Lee, Gyuejeong and Choi, Daeyoung}, title = {Class-Wise Federated Averaging for Efficient Personalization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1773-1782} }
FinMMR: Make Financial Numerical Reasoning More Multimodal, Comprehensive, and Challenging: Zichen Tang,

Haihong E,

Jiacheng Liu,

Zhongjun Yang,

Rongjin Li,

Zihua Rong,

Haoyang He,

Zhuodi Hao,

Xinyang Hu,

Kun Ji,

Ziyan Ma,

Mengyuan Ji,

Jun Zhang,

Chenghao Ma,

Qianhe Zheng,

Yang Liu,

Yiling Huang,

Xinyi Hu,

Qing Huang,

Zijian Xie,

Shiyao Peng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tang_2025_ICCV, author = {Tang, Zichen and E, Haihong and Liu, Jiacheng and Yang, Zhongjun and Li, Rongjin and Rong, Zihua and He, Haoyang and Hao, Zhuodi and Hu, Xinyang and Ji, Kun and Ma, Ziyan and Ji, Mengyuan and Zhang, Jun and Ma, Chenghao and Zheng, Qianhe and Liu, Yang and Huang, Yiling and Hu, Xinyi and Huang, Qing and Xie, Zijian and Peng, Shiyao}, title = {FinMMR: Make Financial Numerical Reasoning More Multimodal, Comprehensive, and Challenging}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3245-3257} }
A Tiny Change, A Giant Leap: Long-Tailed Class-Incremental Learning via Geometric Prototype Alignment: Xinyi Lai,

Luojun Lin,

Weijie Chen,

Yuanlong Yu; [pdf] [supp]
[bibtex]
@InProceedings{Lai_2025_ICCV, author = {Lai, Xinyi and Lin, Luojun and Chen, Weijie and Yu, Yuanlong}, title = {A Tiny Change, A Giant Leap: Long-Tailed Class-Incremental Learning via Geometric Prototype Alignment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1444-1453} }
HORT: Monocular Hand-held Objects Reconstruction with Transformers: Zerui Chen,

Rolandos Alexandros Potamias,

Shizhe Chen,

Cordelia Schmid; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Zerui and Potamias, Rolandos Alexandros and Chen, Shizhe and Schmid, Cordelia}, title = {HORT: Monocular Hand-held Objects Reconstruction with Transformers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6046-6057} }
SplatTalk: 3D VQA with Gaussian Splatting: Anh Thai,

Songyou Peng,

Kyle Genova,

Leonidas Guibas,

Thomas Funkhouser; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Thai_2025_ICCV, author = {Thai, Anh and Peng, Songyou and Genova, Kyle and Guibas, Leonidas and Funkhouser, Thomas}, title = {SplatTalk: 3D VQA with Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4712-4721} }
LocalDyGS: Multi-view Global Dynamic Scene Modeling via Adaptive Local Implicit Feature Decoupling: Jiahao Wu,

Rui Peng,

Jianbo Jiao,

Jiayu Yang,

Luyang Tang,

Kaiqiang Xiong,

Jie Liang,

Jinbo Yan,

Runling Liu,

Ronggang Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2025_ICCV, author = {Wu, Jiahao and Peng, Rui and Jiao, Jianbo and Yang, Jiayu and Tang, Luyang and Xiong, Kaiqiang and Liang, Jie and Yan, Jinbo and Liu, Runling and Wang, Ronggang}, title = {LocalDyGS: Multi-view Global Dynamic Scene Modeling via Adaptive Local Implicit Feature Decoupling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9519-9529} }
Knowledge Distillation for Learned Image Compression: Yunuo Chen,

Zezheng Lyu,

Bing He,

Ning Cao,

Gang Chen,

Guo Lu,

Wenjun Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Yunuo and Lyu, Zezheng and He, Bing and Cao, Ning and Chen, Gang and Lu, Guo and Zhang, Wenjun}, title = {Knowledge Distillation for Learned Image Compression}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4996-5006} }
Unsupervised Identification of Protein Compositions and Conformations via Implicit Content-Transformation Disentanglement: Mostofa Rafid Uddin,

Jana Armouti,

Min Xu; [pdf] [supp]
[bibtex]
@InProceedings{Uddin_2025_ICCV, author = {Uddin, Mostofa Rafid and Armouti, Jana and Xu, Min}, title = {Unsupervised Identification of Protein Compositions and Conformations via Implicit Content-Transformation Disentanglement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7483-7493} }
GenHaze: Pioneering Controllable One-Step Realistic Haze Generation for Real-World Dehazing: Sixiang Chen,

Tian Ye,

Yunlong Lin,

Yeying Jin,

Yijun Yang,

Haoyu Chen,

Jianyu Lai,

Song Fei,

Zhaohu Xing,

Fugee Tsung,

Lei Zhu; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Sixiang and Ye, Tian and Lin, Yunlong and Jin, Yeying and Yang, Yijun and Chen, Haoyu and Lai, Jianyu and Fei, Song and Xing, Zhaohu and Tsung, Fugee and Zhu, Lei}, title = {GenHaze: Pioneering Controllable One-Step Realistic Haze Generation for Real-World Dehazing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9194-9205} }
LLaVA-CoT: Let Vision Language Models Reason Step-by-Step: Guowei Xu,

Peng Jin,

Ziang Wu,

Hao Li,

Yibing Song,

Lichao Sun,

Li Yuan; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2025_ICCV, author = {Xu, Guowei and Jin, Peng and Wu, Ziang and Li, Hao and Song, Yibing and Sun, Lichao and Yuan, Li}, title = {LLaVA-CoT: Let Vision Language Models Reason Step-by-Step}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2087-2098} }
O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views: Lorenzo Mur-Labadia,

Maria Santos-Villafranca,

Jesus Bermudez-Cameo,

Alejandro Perez-Yus,

Ruben Martinez-Cantin,

Jose J. Guerrero; [pdf] [supp]
[bibtex]
@InProceedings{Mur-Labadia_2025_ICCV, author = {Mur-Labadia, Lorenzo and Santos-Villafranca, Maria and Bermudez-Cameo, Jesus and Perez-Yus, Alejandro and Martinez-Cantin, Ruben and Guerrero, Jose J.}, title = {O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6892-6903} }
Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities: Liuyi Wang,

Xinyuan Xia,

Hui Zhao,

Hanqing Wang,

Tai Wang,

Yilun Chen,

Chengju Liu,

Qijun Chen,

Jiangmiao Pang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Liuyi and Xia, Xinyuan and Zhao, Hui and Wang, Hanqing and Wang, Tai and Chen, Yilun and Liu, Chengju and Chen, Qijun and Pang, Jiangmiao}, title = {Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9455-9465} }
ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness: Boqian Li,

Haiwen Feng,

Zeyu Cai,

Michael J. Black,

Yuliang Xiu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Boqian and Feng, Haiwen and Cai, Zeyu and Black, Michael J. and Xiu, Yuliang}, title = {ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8264-8274} }
SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning: Zhi Chen,

Zecheng Zhao,

Jingcai Guo,

Jingjing Li,

Zi Huang; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Zhi and Zhao, Zecheng and Guo, Jingcai and Li, Jingjing and Huang, Zi}, title = {SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3346-3356} }
Forgetting Through Transforming: Enabling Federated Unlearning via Class-Aware Representation Transformation: Qi Guo,

Zhen Tian,

Minghao Yao,

Saiyu Qi,

Yong Qi,

Bingyi Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2025_ICCV, author = {Guo, Qi and Tian, Zhen and Yao, Minghao and Qi, Saiyu and Qi, Yong and Liu, Bingyi}, title = {Forgetting Through Transforming: Enabling Federated Unlearning via Class-Aware Representation Transformation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1474-1483} }
FRET: Feature Redundancy Elimination for Test Time Adaptation: Linjing You,

Jiabao Lu,

Xiayuan Huang,

Xiangli Nie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{You_2025_ICCV, author = {You, Linjing and Lu, Jiabao and Huang, Xiayuan and Nie, Xiangli}, title = {FRET: Feature Redundancy Elimination for Test Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2120-2130} }
From One to More: Contextual Part Latents for 3D Generation: Shaocong Dong,

Lihe Ding,

Xiao Chen,

Yaokun Li,

Yuxin Wang,

Yucheng Wang,

Qi Wang,

Jaehyeok Kim,

Chenjian Gao,

Zhanpeng Huang,

Zibin Wang,

Tianfan Xue,

Dan Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dong_2025_ICCV, author = {Dong, Shaocong and Ding, Lihe and Chen, Xiao and Li, Yaokun and Wang, Yuxin and Wang, Yucheng and Wang, Qi and Kim, Jaehyeok and Gao, Chenjian and Huang, Zhanpeng and Wang, Zibin and Xue, Tianfan and Xu, Dan}, title = {From One to More: Contextual Part Latents for 3D Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8230-8240} }
CL-Splats: Continual Learning of Gaussian Splatting with Local Optimization: Jan Ackermann,

Jonas Kulhanek,

Shengqu Cai,

Haofei Xu,

Marc Pollefeys,

Gordon Wetzstein,

Leonidas J. Guibas,

Songyou Peng; [pdf] [supp]
[bibtex]
@InProceedings{Ackermann_2025_ICCV, author = {Ackermann, Jan and Kulhanek, Jonas and Cai, Shengqu and Xu, Haofei and Pollefeys, Marc and Wetzstein, Gordon and Guibas, Leonidas J. and Peng, Songyou}, title = {CL-Splats: Continual Learning of Gaussian Splatting with Local Optimization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7808-7817} }
PlaneRAS: Learning Planar Primitives for 3D Plane Recovery: Fang Zhang,

Wenzhao Zheng,

Linqing Zhao,

Zelan Zhu,

Jiwen Lu,

Xiuzhuang Zhou; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Fang and Zheng, Wenzhao and Zhao, Linqing and Zhu, Zelan and Lu, Jiwen and Zhou, Xiuzhuang}, title = {PlaneRAS: Learning Planar Primitives for 3D Plane Recovery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6882-6891} }
Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models: Xinyu Chen,

Haotian Zhai,

Can Zhang,

Xiupeng Shi,

Ruirui Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Xinyu and Zhai, Haotian and Zhang, Can and Shi, Xiupeng and Li, Ruirui}, title = {Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2281-2291} }
Understanding Flatness in Generative Models: Its Role and Benefits: Taehwan Lee,

Kyeongkook Seo,

Jaejun Yoo,

Sung Whan Yoon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2025_ICCV, author = {Lee, Taehwan and Seo, Kyeongkook and Yoo, Jaejun and Yoon, Sung Whan}, title = {Understanding Flatness in Generative Models: Its Role and Benefits}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4908-4917} }
DCHM: Depth-Consistent Human Modeling for Multiview Detection: Jiahao Ma,

Tianyu Wang,

Miaomiao Liu,

David Ahmedt-Aristizabal,

Chuong Nguyen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2025_ICCV, author = {Ma, Jiahao and Wang, Tianyu and Liu, Miaomiao and Ahmedt-Aristizabal, David and Nguyen, Chuong}, title = {DCHM: Depth-Consistent Human Modeling for Multiview Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7731-7740} }
GeoExplorer: Active Geo-localization with Curiosity-Driven Exploration: Li Mi,

Manon Béchaz,

Zeming Chen,

Antoine Bosselut,

Devis Tuia; [pdf] [supp]
[bibtex]
@InProceedings{Mi_2025_ICCV, author = {Mi, Li and B\'echaz, Manon and Chen, Zeming and Bosselut, Antoine and Tuia, Devis}, title = {GeoExplorer: Active Geo-localization with Curiosity-Driven Exploration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6122-6131} }
Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction: Weirong Chen,

Ganlin Zhang,

Felix Wimbauer,

Rui Wang,

Nikita Araslanov,

Andrea Vedaldi,

Daniel Cremers; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Weirong and Zhang, Ganlin and Wimbauer, Felix and Wang, Rui and Araslanov, Nikita and Vedaldi, Andrea and Cremers, Daniel}, title = {Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4951-4960} }
NegRefine: Refining Negative Label-Based Zero-Shot OOD Detection: Amirhossein Ansari,

Ke Wang,

Pulei Xiong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ansari_2025_ICCV, author = {Ansari, Amirhossein and Wang, Ke and Xiong, Pulei}, title = {NegRefine: Refining Negative Label-Based Zero-Shot OOD Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {573-582} }
ACAM-KD: Adaptive and Cooperative Attention Masking for Knowledge Distillation: Qizhen Lan,

Qing Tian; [pdf]
[bibtex]
@InProceedings{Lan_2025_ICCV, author = {Lan, Qizhen and Tian, Qing}, title = {ACAM-KD: Adaptive and Cooperative Attention Masking for Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3957-3966} }
Completing 3D Partial Assemblies with View-Consistent 2D-3D Correspondence: Weihao Wang,

Yu Lan,

Mingyu You,

Bin He; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Weihao and Lan, Yu and You, Mingyu and He, Bin}, title = {Completing 3D Partial Assemblies with View-Consistent 2D-3D Correspondence}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7741-7750} }
Latte: Collaborative Test-Time Adaptation of Vision-Language Models in Federated Learning: Wenxuan Bao,

Ruxi Deng,

Ruizhong Qiu,

Tianxin Wei,

Hanghang Tong,

Jingrui He; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bao_2025_ICCV, author = {Bao, Wenxuan and Deng, Ruxi and Qiu, Ruizhong and Wei, Tianxin and Tong, Hanghang and He, Jingrui}, title = {Latte: Collaborative Test-Time Adaptation of Vision-Language Models in Federated Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {133-143} }
One-Shot Knowledge Transfer for Scalable Person Re-Identification: Longhua Li,

Lei Qi,

Xin Geng; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Longhua and Qi, Lei and Geng, Xin}, title = {One-Shot Knowledge Transfer for Scalable Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {668-677} }
SAS: Segment Any 3D Scene with Integrated 2D Priors: Zhuoyuan Li,

Jiahao Lu,

Jiacheng Deng,

Hanzhi Chang,

Lifan Wu,

Yanzhe Liang,

Tianzhu Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Zhuoyuan and Lu, Jiahao and Deng, Jiacheng and Chang, Hanzhi and Wu, Lifan and Liang, Yanzhe and Zhang, Tianzhu}, title = {SAS: Segment Any 3D Scene with Integrated 2D Priors}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8306-8318} }
OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration: Yiming Zuo,

Willow Yang,

Zeyu Ma,

Jia Deng; [pdf] [supp]
[bibtex]
@InProceedings{Zuo_2025_ICCV, author = {Zuo, Yiming and Yang, Willow and Ma, Zeyu and Deng, Jia}, title = {OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9287-9297} }
PHD: Personalized 3D Human Body Fitting with Point Diffusion: Hsuan-I Ho,

Chen Guo,

Po-Chen Wu,

Ivan Shugurov,

Chengcheng Tang,

Abhay Mittal,

Sizhe An,

Manuel Kaufmann,

Linguang Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ho_2025_ICCV, author = {Ho, Hsuan-I and Guo, Chen and Wu, Po-Chen and Shugurov, Ivan and Tang, Chengcheng and Mittal, Abhay and An, Sizhe and Kaufmann, Manuel and Zhang, Linguang}, title = {PHD: Personalized 3D Human Body Fitting with Point Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7526-7537} }
Hierarchical Material Recognition from Local Appearance: Matthew Beveridge,

Shree K. Nayar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Beveridge_2025_ICCV, author = {Beveridge, Matthew and Nayar, Shree K.}, title = {Hierarchical Material Recognition from Local Appearance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8165-8176} }
Unleashing the Temporal Potential of Stereo Event Cameras for Continuous-Time 3D Object Detection: Jae-Young Kang,

Hoonhee Cho,

Kuk-Jin Yoon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kang_2025_ICCV, author = {Kang, Jae-Young and Cho, Hoonhee and Yoon, Kuk-Jin}, title = {Unleashing the Temporal Potential of Stereo Event Cameras for Continuous-Time 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6869-6881} }
R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization: Jingyi Zhang,

Jiaxing Huang,

Huanjin Yao,

Shunyu Liu,

Xikun Zhang,

Shijian Lu,

Dacheng Tao; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Jingyi and Huang, Jiaxing and Yao, Huanjin and Liu, Shunyu and Zhang, Xikun and Lu, Shijian and Tao, Dacheng}, title = {R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1859-1869} }
Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning: Zedong Wang,

Siyuan Li,

Dan Xu; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Zedong and Li, Siyuan and Xu, Dan}, title = {Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3413-3423} }
Region-based Cluster Discrimination for Visual Representation Learning: Yin Xie,

Kaicheng Yang,

Xiang An,

Kun Wu,

Yongle Zhao,

Weimo Deng,

Zimin Ran,

Yumeng Wang,

Ziyong Feng,

Roy Miles,

Ismail Elezi,

Jiankang Deng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xie_2025_ICCV, author = {Xie, Yin and Yang, Kaicheng and An, Xiang and Wu, Kun and Zhao, Yongle and Deng, Weimo and Ran, Zimin and Wang, Yumeng and Feng, Ziyong and Miles, Roy and Elezi, Ismail and Deng, Jiankang}, title = {Region-based Cluster Discrimination for Visual Representation Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1793-1803} }
EvRT-DETR: Latent Space Adaptation of Image Detectors for Event-based Vision: Dmitrii Torbunov,

Yihui Ren,

Animesh Ghose,

Odera Dim,

Yonggang Cui; [pdf] [supp]
[bibtex]
@InProceedings{Torbunov_2025_ICCV, author = {Torbunov, Dmitrii and Ren, Yihui and Ghose, Animesh and Dim, Odera and Cui, Yonggang}, title = {EvRT-DETR: Latent Space Adaptation of Image Detectors for Event-based Vision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9812-9821} }
Easi3R: Estimating Disentangled Motion from DUSt3R Without Training: Xingyu Chen,

Yue Chen,

Yuliang Xiu,

Andreas Geiger,

Anpei Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Xingyu and Chen, Yue and Xiu, Yuliang and Geiger, Andreas and Chen, Anpei}, title = {Easi3R: Estimating Disentangled Motion from DUSt3R Without Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9158-9168} }
CaO2: Rectifying Inconsistencies in Diffusion-Based Dataset Distillation: Haoxuan Wang,

Zhenghao Zhao,

Junyi Wu,

Yuzhang Shang,

Gaowen Liu,

Yan Yan; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Haoxuan and Zhao, Zhenghao and Wu, Junyi and Shang, Yuzhang and Liu, Gaowen and Yan, Yan}, title = {CaO2: Rectifying Inconsistencies in Diffusion-Based Dataset Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4722-4731} }
Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective: Hoang Phan,

Lam Tran,

Quyen Tran,

Ngoc Tran,

Tuan Truong,

Qi Lei,

Nhat Ho,

Dinh Phung,

Trung Le; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Phan_2025_ICCV, author = {Phan, Hoang and Tran, Lam and Tran, Quyen and Tran, Ngoc and Truong, Tuan and Lei, Qi and Ho, Nhat and Phung, Dinh and Le, Trung}, title = {Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2440-2450} }
Zero-shot Inexact CAD Model Alignment from a Single Image: Pattaramanee Arsomngern,

Sasikarn Khwanmuang,

Matthias Nießner,

Supasorn Suwajanakorn; [pdf] [supp]
[bibtex]
@InProceedings{Arsomngern_2025_ICCV, author = {Arsomngern, Pattaramanee and Khwanmuang, Sasikarn and Nie{\ss}ner, Matthias and Suwajanakorn, Supasorn}, title = {Zero-shot Inexact CAD Model Alignment from a Single Image}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6231-6241} }
Cycle-Consistent Learning for Joint Layout-to-Image Generation and Object Detection: Xinhao Cai,

Qiuxia Lai,

Gensheng Pei,

Xiangbo Shu,

Yazhou Yao,

Wenguan Wang; [pdf] [supp]
[bibtex]
@InProceedings{Cai_2025_ICCV, author = {Cai, Xinhao and Lai, Qiuxia and Pei, Gensheng and Shu, Xiangbo and Yao, Yazhou and Wang, Wenguan}, title = {Cycle-Consistent Learning for Joint Layout-to-Image Generation and Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6797-6807} }
LIFT: Latent Implicit Functions for Task- and Data-Agnostic Encoding: Amirhossein Kazerouni,

Soroush Mehraban,

Michael Brudno,

Babak Taati; [pdf] [supp]
[bibtex]
@InProceedings{Kazerouni_2025_ICCV, author = {Kazerouni, Amirhossein and Mehraban, Soroush and Brudno, Michael and Taati, Babak}, title = {LIFT: Latent Implicit Functions for Task- and Data-Agnostic Encoding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4828-4837} }
Long-Context State-Space Video World Models: Ryan Po,

Yotam Nitzan,

Richard Zhang,

Berlin Chen,

Tri Dao,

Eli Shechtman,

Gordon Wetzstein,

Xun Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Po_2025_ICCV, author = {Po, Ryan and Nitzan, Yotam and Zhang, Richard and Chen, Berlin and Dao, Tri and Shechtman, Eli and Wetzstein, Gordon and Huang, Xun}, title = {Long-Context State-Space Video World Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8733-8744} }
Dataset Distillation via the Wasserstein Metric: Haoyang Liu,

Yijiang Li,

Tiancheng Xing,

Peiran Wang,

Vibhu Dalal,

Luwei Li,

Jingrui He,

Haohan Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2025_ICCV, author = {Liu, Haoyang and Li, Yijiang and Xing, Tiancheng and Wang, Peiran and Dalal, Vibhu and Li, Luwei and He, Jingrui and Wang, Haohan}, title = {Dataset Distillation via the Wasserstein Metric}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1205-1215} }
IRGPT: Understanding Real-world Infrared Image with Bi-cross-modal Curriculum on Large-scale Benchmark: Zhe Cao,

Jin Zhang,

Ruiheng Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2025_ICCV, author = {Cao, Zhe and Zhang, Jin and Zhang, Ruiheng}, title = {IRGPT: Understanding Real-world Infrared Image with Bi-cross-modal Curriculum on Large-scale Benchmark}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {166-176} }
Efficient Visual Place Recognition Through Multimodal Semantic Knowledge Integration: Sitao Zhang,

Hongda Mao,

Qingshuang Chen,

Yelin Kim; [pdf]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Sitao and Mao, Hongda and Chen, Qingshuang and Kim, Yelin}, title = {Efficient Visual Place Recognition Through Multimodal Semantic Knowledge Integration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5601-5610} }
Rethinking Multi-modal Object Detection from the Perspective of Mono-Modality Feature Learning: Tianyi Zhao,

Boyang Liu,

Yanglei Gao,

Yiming Sun,

Maoxun Yuan,

Xingxing Wei; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhao_2025_ICCV, author = {Zhao, Tianyi and Liu, Boyang and Gao, Yanglei and Sun, Yiming and Yuan, Maoxun and Wei, Xingxing}, title = {Rethinking Multi-modal Object Detection from the Perspective of Mono-Modality Feature Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6364-6373} }
Task-Aware Prompt Gradient Projection for Parameter-Efficient Tuning Federated Class-Incremental Learning: Hualong Ke,

Jiangming Shi,

Yachao Zhang,

Fangyong Wang,

Yuan Xie,

Yanyun Qu; [pdf] [supp]
[bibtex]
@InProceedings{Ke_2025_ICCV, author = {Ke, Hualong and Shi, Jiangming and Zhang, Yachao and Wang, Fangyong and Xie, Yuan and Qu, Yanyun}, title = {Task-Aware Prompt Gradient Projection for Parameter-Efficient Tuning Federated Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2631-2641} }
Intervening in Black Box: Concept Bottleneck Model for Enhancing Human Neural Network Mutual Understanding: Nuoye Xiong,

Anqi Dong,

Ning Wang,

Cong Hua,

Guangming Zhu,

Lin Mei,

Peiyi Shen,

Liang Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiong_2025_ICCV, author = {Xiong, Nuoye and Dong, Anqi and Wang, Ning and Hua, Cong and Zhu, Guangming and Mei, Lin and Shen, Peiyi and Zhang, Liang}, title = {Intervening in Black Box: Concept Bottleneck Model for Enhancing Human Neural Network Mutual Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2836-2845} }
Shape of Motion: 4D Reconstruction from a Single Video: Qianqian Wang,

Vickie Ye,

Hang Gao,

Weijia Zeng,

Jake Austin,

Zhengqi Li,

Angjoo Kanazawa; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Qianqian and Ye, Vickie and Gao, Hang and Zeng, Weijia and Austin, Jake and Li, Zhengqi and Kanazawa, Angjoo}, title = {Shape of Motion: 4D Reconstruction from a Single Video}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9660-9672} }
Backdoor Defense via Enhanced Splitting and Trap Isolation: Hongrui Yu,

Lu Qi,

Wanyu Lin,

Jian Chen,

Hailong Sun,

Chengbin Sun; [pdf] [supp]
[bibtex]
@InProceedings{Yu_2025_ICCV, author = {Yu, Hongrui and Qi, Lu and Lin, Wanyu and Chen, Jian and Sun, Hailong and Sun, Chengbin}, title = {Backdoor Defense via Enhanced Splitting and Trap Isolation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1708-1717} }
FedVLA: Federated Vision-Language-Action Learning with Dual Gating Mixture-of-Experts for Robotic Manipulation: Cui Miao,

Tao Chang,

Meihan Wu,

Hongbin Xu,

Chun Li,

Ming Li,

Xiaodong Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Miao_2025_ICCV, author = {Miao, Cui and Chang, Tao and Wu, Meihan and Xu, Hongbin and Li, Chun and Li, Ming and Wang, Xiaodong}, title = {FedVLA: Federated Vision-Language-Action Learning with Dual Gating Mixture-of-Experts for Robotic Manipulation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6904-6913} }
BokehDiff: Neural Lens Blur with One-Step Diffusion: Chengxuan Zhu,

Qingnan Fan,

Qi Zhang,

Jinwei Chen,

Huaqi Zhang,

Chao Xu,

Boxin Shi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2025_ICCV, author = {Zhu, Chengxuan and Fan, Qingnan and Zhang, Qi and Chen, Jinwei and Zhang, Huaqi and Xu, Chao and Shi, Boxin}, title = {BokehDiff: Neural Lens Blur with One-Step Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9508-9518} }
Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation: Phillip Y. Lee,

Jihyeon Je,

Chanho Park,

Mikaela Angelina Uy,

Leonidas Guibas,

Minhyuk Sung; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2025_ICCV, author = {Lee, Phillip Y. and Je, Jihyeon and Park, Chanho and Uy, Mikaela Angelina and Guibas, Leonidas and Sung, Minhyuk}, title = {Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9241-9251} }
PASG: A Closed-Loop Framework for Automated Geometric Primitive Extraction and Semantic Anchoring in Robotic Manipulation: Zhihao Zhu,

Yifan Zheng,

Siyu Pan,

Yaohui Jin,

Yao Mu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2025_ICCV, author = {Zhu, Zhihao and Zheng, Yifan and Pan, Siyu and Jin, Yaohui and Mu, Yao}, title = {PASG: A Closed-Loop Framework for Automated Geometric Primitive Extraction and Semantic Anchoring in Robotic Manipulation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8950-8960} }
Registration beyond Points: General Affine Subspace Alignment via Geodesic Distance on Grassmann Manifold: Jaeho Shin,

Hyeonjae Gil,

Junwoo Jang,

Maani Ghaffari,

Ayoung Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shin_2025_ICCV, author = {Shin, Jaeho and Gil, Hyeonjae and Jang, Junwoo and Ghaffari, Maani and Kim, Ayoung}, title = {Registration beyond Points: General Affine Subspace Alignment via Geodesic Distance on Grassmann Manifold}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3767-3776} }
Amodal Depth Anything: Amodal Depth Estimation in the Wild: Zhenyu Li,

Mykola Lavreniuk,

Jian Shi,

Shariq Farooq Bhat,

Peter Wonka; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Zhenyu and Lavreniuk, Mykola and Shi, Jian and Bhat, Shariq Farooq and Wonka, Peter}, title = {Amodal Depth Anything: Amodal Depth Estimation in the Wild}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9673-9682} }
Hierarchical Variational Test-Time Prompt Generation for Zero-Shot Generalization: Zhaoyang Wu,

Fang Liu,

Licheng Jiao,

Shuo Li,

Lingling Li,

Xu Liu,

Puhua Chen,

Wenping Ma; [pdf]
[bibtex]
@InProceedings{Wu_2025_ICCV, author = {Wu, Zhaoyang and Liu, Fang and Jiao, Licheng and Li, Shuo and Li, Lingling and Liu, Xu and Chen, Puhua and Ma, Wenping}, title = {Hierarchical Variational Test-Time Prompt Generation for Zero-Shot Generalization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2325-2335} }
Towards Long-Horizon Vision-Language-Action System: Reasoning, Acting and Memory: Daixun Li,

Yusi Zhang,

Mingxiang Cao,

Donglai Liu,

Weiying Xie,

Tianlin Hui,

Lunkai Lin,

Zhiqiang Xie,

Yunsong Li; [pdf]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Daixun and Zhang, Yusi and Cao, Mingxiang and Liu, Donglai and Xie, Weiying and Hui, Tianlin and Lin, Lunkai and Xie, Zhiqiang and Li, Yunsong}, title = {Towards Long-Horizon Vision-Language-Action System: Reasoning, Acting and Memory}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6839-6848} }
Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition: Zhisheng Zhong,

Chengyao Wang,

Yuqi Liu,

Senqiao Yang,

Longxiang Tang,

Yuechen Zhang,

Jingyao Li,

Tianyuan Qu,

Yanwei Li,

Yukang Chen,

Shaozuo Yu,

Sitong Wu,

Eric Lo,

Shu Liu,

Jiaya Jia; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhong_2025_ICCV, author = {Zhong, Zhisheng and Wang, Chengyao and Liu, Yuqi and Yang, Senqiao and Tang, Longxiang and Zhang, Yuechen and Li, Jingyao and Qu, Tianyuan and Li, Yanwei and Chen, Yukang and Yu, Shaozuo and Wu, Sitong and Lo, Eric and Liu, Shu and Jia, Jiaya}, title = {Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3694-3704} }
PacGDC: Label-Efficient Generalizable Depth Completion with Projection Ambiguity and Consistency: Haotian Wang,

Aoran Xiao,

Xiaoqin Zhang,

Meng Yang,

Shijian Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Haotian and Xiao, Aoran and Zhang, Xiaoqin and Yang, Meng and Lu, Shijian}, title = {PacGDC: Label-Efficient Generalizable Depth Completion with Projection Ambiguity and Consistency}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7709-7720} }
GSV3D: Gaussian Splatting-based Geometric Distillation with Stable Video Diffusion for Single-Image 3D Object Generation: Ye Tao,

Jiawei Zhang,

Yahao Shi,

Dongqing Zou,

Bin Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tao_2025_ICCV, author = {Tao, Ye and Zhang, Jiawei and Shi, Yahao and Zou, Dongqing and Zhou, Bin}, title = {GSV3D: Gaussian Splatting-based Geometric Distillation with Stable Video Diffusion for Single-Image 3D Object Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7751-7760} }
Guiding Diffusion-Based Articulated Object Generation by Partial Point Cloud Alignment and Physical Plausibility Constraints: Jens U. Kreber,

Joerg Stueckler; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kreber_2025_ICCV, author = {Kreber, Jens U. and Stueckler, Joerg}, title = {Guiding Diffusion-Based Articulated Object Generation by Partial Point Cloud Alignment and Physical Plausibility Constraints}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3206-3214} }
PoseSyn: Synthesizing Diverse 3D Pose Data from In-the-Wild 2D Data: ChangHee Yang,

Hyeonseop Song,

Seokhun Choi,

Seungwoo Lee,

Jaechul Kim,

Hoseok Do; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, ChangHee and Song, Hyeonseop and Choi, Seokhun and Lee, Seungwoo and Kim, Jaechul and Do, Hoseok}, title = {PoseSyn: Synthesizing Diverse 3D Pose Data from In-the-Wild 2D Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5611-5621} }
Backdoor Attacks on Neural Networks via One-Bit Flip: Xiang Li,

Lannan Luo,

Qiang Zeng; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Xiang and Luo, Lannan and Zeng, Qiang}, title = {Backdoor Attacks on Neural Networks via One-Bit Flip}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4328-4338} }
Enhancing Adversarial Transferability by Balancing Exploration and Exploitation with Gradient-Guided Sampling: Zenghao Niu,

Weicheng Xie,

Siyang Song,

Zitong Yu,

Feng Liu,

Linlin Shen; [pdf] [supp]
[bibtex]
@InProceedings{Niu_2025_ICCV, author = {Niu, Zenghao and Xie, Weicheng and Song, Siyang and Yu, Zitong and Liu, Feng and Shen, Linlin}, title = {Enhancing Adversarial Transferability by Balancing Exploration and Exploitation with Gradient-Guided Sampling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3885-3894} }
External Knowledge Injection for CLIP-Based Class-Incremental Learning: Da-Wei Zhou,

Kai-Wen Li,

Jingyi Ning,

Han-Jia Ye,

Lijun Zhang,

De-Chuan Zhan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2025_ICCV, author = {Zhou, Da-Wei and Li, Kai-Wen and Ning, Jingyi and Ye, Han-Jia and Zhang, Lijun and Zhan, De-Chuan}, title = {External Knowledge Injection for CLIP-Based Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3314-3325} }
GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields: Shunsuke Yasuki,

Taiki Miyanishi,

Nakamasa Inoue,

Shuhei Kurita,

Koya Sakamoto,

Daichi Azuma,

Masato Taki,

Yutaka Matsuo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yasuki_2025_ICCV, author = {Yasuki, Shunsuke and Miyanishi, Taiki and Inoue, Nakamasa and Kurita, Shuhei and Sakamoto, Koya and Azuma, Daichi and Taki, Masato and Matsuo, Yutaka}, title = {GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9737-9748} }
Geometry Distributions: Biao Zhang,

Jing Ren,

Peter Wonka; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Biao and Ren, Jing and Wonka, Peter}, title = {Geometry Distributions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1495-1505} }
Low-Light Image Enhancement Using Event-Based Illumination Estimation: Lei Sun,

Yuhan Bao,

Jiajun Zhai,

Jingyun Liang,

Yulun Zhang,

Kaiwei Wang,

Danda Pani Paudel,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2025_ICCV, author = {Sun, Lei and Bao, Yuhan and Zhai, Jiajun and Liang, Jingyun and Zhang, Yulun and Wang, Kaiwei and Paudel, Danda Pani and Van Gool, Luc}, title = {Low-Light Image Enhancement Using Event-Based Illumination Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6667-6677} }
A Good Teacher Adapts Their Knowledge for Distillation: Chengyao Qian,

Trung Le,

Mehrtash Harandi; [pdf] [supp]
[bibtex]
@InProceedings{Qian_2025_ICCV, author = {Qian, Chengyao and Le, Trung and Harandi, Mehrtash}, title = {A Good Teacher Adapts Their Knowledge for Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1239-1248} }
Semi-supervised Deep Transfer for Regression without Domain Alignment: Mainak Biswas,

Ambedkar Dukkipati,

Devarajan Sridharan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Biswas_2025_ICCV, author = {Biswas, Mainak and Dukkipati, Ambedkar and Sridharan, Devarajan}, title = {Semi-supervised Deep Transfer for Regression without Domain Alignment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {827-836} }
Evading Data Provenance in Deep Neural Networks: Hongyu Zhu,

Sichu Liang,

Wenwen Wang,

Zhuomeng Zhang,

Fangqi Li,

Shi-Lin Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2025_ICCV, author = {Zhu, Hongyu and Liang, Sichu and Wang, Wenwen and Zhang, Zhuomeng and Li, Fangqi and Wang, Shi-Lin}, title = {Evading Data Provenance in Deep Neural Networks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1249-1260} }
Manual-PA: Learning 3D Part Assembly from Instruction Diagrams: Jiahao Zhang,

Anoop Cherian,

Cristian Rodriguez,

Weijian Deng,

Stephen Gould; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Jiahao and Cherian, Anoop and Rodriguez, Cristian and Deng, Weijian and Gould, Stephen}, title = {Manual-PA: Learning 3D Part Assembly from Instruction Diagrams}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6304-6314} }
RMultiplex200K: Toward Reliable Multimodal Process Supervision for Visual Language Models on Telecommunications: Sijia Chen,

Bin Song; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Sijia and Song, Bin}, title = {RMultiplex200K: Toward Reliable Multimodal Process Supervision for Visual Language Models on Telecommunications}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1686-1696} }
CA2C: A Prior-Knowledge-Free Approach for Robust Label Noise Learning via Asymmetric Co-learning and Co-training: Mengmeng Sheng,

Zeren Sun,

Tianfei Zhou,

Xiangbo Shu,

Jinshan Pan,

Yazhou Yao; [pdf]
[bibtex]
@InProceedings{Sheng_2025_ICCV, author = {Sheng, Mengmeng and Sun, Zeren and Zhou, Tianfei and Shu, Xiangbo and Pan, Jinshan and Yao, Yazhou}, title = {CA2C: A Prior-Knowledge-Free Approach for Robust Label Noise Learning via Asymmetric Co-learning and Co-training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {901-911} }
Prototype-based Contrastive Learning with Stage-wise Progressive Augmentation for Self-Supervised Fine-Grained Learning: Baofeng Tan,

Xiu-Shen Wei,

Lin Zhao; [pdf] [supp]
[bibtex]
@InProceedings{Tan_2025_ICCV, author = {Tan, Baofeng and Wei, Xiu-Shen and Zhao, Lin}, title = {Prototype-based Contrastive Learning with Stage-wise Progressive Augmentation for Self-Supervised Fine-Grained Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4125-4134} }
4DSegStreamer: Streaming 4D Panoptic Segmentation via Dual Threads: Ling Liu,

Jun Tian,

Li Yi; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2025_ICCV, author = {Liu, Ling and Tian, Jun and Yi, Li}, title = {4DSegStreamer: Streaming 4D Panoptic Segmentation via Dual Threads}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7089-7098} }
TWIST & SCOUT: Grounding Multimodal LLM-Experts by Forget-Free Tuning: Aritra Bhowmik,

Mohammad Mahdi Derakhshani,

Dennis Koelma,

Yuki M. Asano,

Martin R. Oswald,

Cees G. M. Snoek; [pdf] [arXiv]
[bibtex]
@InProceedings{Bhowmik_2025_ICCV, author = {Bhowmik, Aritra and Derakhshani, Mohammad Mahdi and Koelma, Dennis and Asano, Yuki M. and Oswald, Martin R. and Snoek, Cees G. M.}, title = {TWIST \& SCOUT: Grounding Multimodal LLM-Experts by Forget-Free Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1359-1368} }
VSP: Diagnosing the Dual Challenges of Perception and Reasoning in Spatial Planning Tasks for MLLMs: Qiucheng Wu,

Handong Zhao,

Michael Saxon,

Trung Bui,

William Yang Wang,

Yang Zhang,

Shiyu Chang; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2025_ICCV, author = {Wu, Qiucheng and Zhao, Handong and Saxon, Michael and Bui, Trung and Wang, William Yang and Zhang, Yang and Chang, Shiyu}, title = {VSP: Diagnosing the Dual Challenges of Perception and Reasoning in Spatial Planning Tasks for MLLMs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2270-2280} }
Instance-Level Video Depth in Groups Beyond Occlusions: Yuan Liang,

Yang Zhou,

Ziming Sun,

Tianyi Xiang,

Guiqing Li,

Shengfeng He; [pdf]
[bibtex]
@InProceedings{Liang_2025_ICCV, author = {Liang, Yuan and Zhou, Yang and Sun, Ziming and Xiang, Tianyi and Li, Guiqing and He, Shengfeng}, title = {Instance-Level Video Depth in Groups Beyond Occlusions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7581-7591} }
ODP-Bench: Benchmarking Out-of-Distribution Performance Prediction: Han Yu,

Kehan Li,

Dongbai Li,

Yue He,

Xingxuan Zhang,

Peng Cui; [pdf]
[bibtex]
@InProceedings{Yu_2025_ICCV, author = {Yu, Han and Li, Kehan and Li, Dongbai and He, Yue and Zhang, Xingxuan and Cui, Peng}, title = {ODP-Bench: Benchmarking Out-of-Distribution Performance Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1846-1858} }
Sibai: A Few-Shot Meta-Classifier for Poisoning Detection in Federated Learning: Melanie Götz,

Torsten Krauß,

Alexandra Dmitrienko; [pdf] [supp]
[bibtex]
@InProceedings{Gotz_2025_ICCV, author = {G\"otz, Melanie and Krau{\ss}, Torsten and Dmitrienko, Alexandra}, title = {Sibai: A Few-Shot Meta-Classifier for Poisoning Detection in Federated Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3787-3797} }
Generative Modeling of Shape-Dependent Self-Contact Human Poses: Takehiko Ohkawa,

Jihyun Lee,

Shunsuke Saito,

Jason Saragih,

Fabian Prada,

Yichen Xu,

Shoou-I Yu,

Ryosuke Furuta,

Yoichi Sato,

Takaaki Shiratori; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ohkawa_2025_ICCV, author = {Ohkawa, Takehiko and Lee, Jihyun and Saito, Shunsuke and Saragih, Jason and Prada, Fabian and Xu, Yichen and Yu, Shoou-I and Furuta, Ryosuke and Sato, Yoichi and Shiratori, Takaaki}, title = {Generative Modeling of Shape-Dependent Self-Contact Human Poses}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5426-5436} }
DAP-MAE: Domain-Adaptive Point Cloud Masked Autoencoder for Effective Cross-Domain Learning: Ziqi Gao,

Qiufu Li,

Linlin Shen; [pdf] [supp]
[bibtex]
@InProceedings{Gao_2025_ICCV, author = {Gao, Ziqi and Li, Qiufu and Shen, Linlin}, title = {DAP-MAE: Domain-Adaptive Point Cloud Masked Autoencoder for Effective Cross-Domain Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3488-3498} }
6DOPE-GS: Online 6D Object Pose Estimation using Gaussian Splatting: Yufeng Jin,

Vignesh Prasad,

Snehal Jauhri,

Mathias Franzius,

Georgia Chalvatzaki; [pdf] [supp]
[bibtex]
@InProceedings{Jin_2025_ICCV, author = {Jin, Yufeng and Prasad, Vignesh and Jauhri, Snehal and Franzius, Mathias and Chalvatzaki, Georgia}, title = {6DOPE-GS: Online 6D Object Pose Estimation using Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8032-8043} }
PLMP - Point-Line Minimal Problems for Projective SfM: Kim Kiehn,

Albin Ahlbäck,

Kathlén Kohn; [pdf] [supp]
[bibtex]
@InProceedings{Kiehn_2025_ICCV, author = {Kiehn, Kim and Ahlb\"ack, Albin and Kohn, Kathl\'en}, title = {PLMP - Point-Line Minimal Problems for Projective SfM}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8558-8567} }
Enhancing Transferability of Targeted Adversarial Examples via Inverse Target Gradient Competition and Spatial Distance Stretching: Zhankai Li,

Weiping Wang,

Jie Li,

Shigeng Zhang,

Yunan Hu,

Song Guo; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Zhankai and Wang, Weiping and Li, Jie and Zhang, Shigeng and Hu, Yunan and Guo, Song}, title = {Enhancing Transferability of Targeted Adversarial Examples via Inverse Target Gradient Competition and Spatial Distance Stretching}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3716-3725} }
A Conditional Probability Framework for Compositional Zero-shot Learning: Peng Wu,

Qiuxia Lai,

Hao Fang,

Guo-Sen Xie,

Yilong Yin,

Xiankai Lu,

Wenguan Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2025_ICCV, author = {Wu, Peng and Lai, Qiuxia and Fang, Hao and Xie, Guo-Sen and Yin, Yilong and Lu, Xiankai and Wang, Wenguan}, title = {A Conditional Probability Framework for Compositional Zero-shot Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3673-3683} }
Advancing Textual Prompt Learning with Anchored Attributes: Zheng Li,

Yibing Song,

Ming-Ming Cheng,

Xiang Li,

Jian Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Zheng and Song, Yibing and Cheng, Ming-Ming and Li, Xiang and Yang, Jian}, title = {Advancing Textual Prompt Learning with Anchored Attributes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3618-3627} }
Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation: Jie Xu,

Na Zhao,

Gang Niu,

Masashi Sugiyama,

Xiaofeng Zhu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2025_ICCV, author = {Xu, Jie and Zhao, Na and Niu, Gang and Sugiyama, Masashi and Zhu, Xiaofeng}, title = {Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4232-4241} }
Fine-Grained Evaluation of Large Vision-Language Models in Autonomous Driving: Yue Li,

Meng Tian,

Zhenyu Lin,

Jiangtong Zhu,

Dechang Zhu,

Haiqiang Liu,

Yueyi Zhang,

Zhiwei Xiong,

Xinhai Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Yue and Tian, Meng and Lin, Zhenyu and Zhu, Jiangtong and Zhu, Dechang and Liu, Haiqiang and Zhang, Yueyi and Xiong, Zhiwei and Zhao, Xinhai}, title = {Fine-Grained Evaluation of Large Vision-Language Models in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9431-9442} }
SCAN: Bootstrapping Contrastive Pre-training for Data Efficiency: Yangyang Guo,

Mohan Kankanhalli; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2025_ICCV, author = {Guo, Yangyang and Kankanhalli, Mohan}, title = {SCAN: Bootstrapping Contrastive Pre-training for Data Efficiency}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3662-3672} }
Diffusion-based Source-biased Model for Single Domain Generalized Object Detection: Han Jiang,

Wenfei Yang,

Tianzhu Zhang,

Yongdong Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Jiang_2025_ICCV, author = {Jiang, Han and Yang, Wenfei and Zhang, Tianzhu and Zhang, Yongdong}, title = {Diffusion-based Source-biased Model for Single Domain Generalized Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1548-1557} }
Diffusion-based 3D Hand Motion Recovery with Intuitive Physics: Yufei Zhang,

Zijun Cui,

Jeffrey O. Kephart,

Qiang Ji; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Yufei and Cui, Zijun and Kephart, Jeffrey O. and Ji, Qiang}, title = {Diffusion-based 3D Hand Motion Recovery with Intuitive Physics}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7306-7317} }
Leveraging Spatial Invariance to Boost Adversarial Transferability: Zihan Zhou,

Li Li,

Yanli Ren,

Chuan Qin,

Guorui Feng; [pdf]
[bibtex]
@InProceedings{Zhou_2025_ICCV, author = {Zhou, Zihan and Li, Li and Ren, Yanli and Qin, Chuan and Feng, Guorui}, title = {Leveraging Spatial Invariance to Boost Adversarial Transferability}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1423-1432} }
MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning: Mohammadreza Salehi,

Shashanka Venkataramanan,

Ioana Simion,

Efstratios Gavves,

Cees G. M. Snoek,

Yuki M Asano; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Salehi_2025_ICCV, author = {Salehi, Mohammadreza and Venkataramanan, Shashanka and Simion, Ioana and Gavves, Efstratios and Snoek, Cees G. M. and Asano, Yuki M}, title = {MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6541-6551} }
MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs: Erik Daxberger,

Nina Wenzel,

David Griffiths,

Haiming Gang,

Justin Lazarow,

Gefen Kohavi,

Kai Kang,

Marcin Eichner,

Yinfei Yang,

Afshin Dehghan,

Peter Grasch; [pdf] [supp]
[bibtex]
@InProceedings{Daxberger_2025_ICCV, author = {Daxberger, Erik and Wenzel, Nina and Griffiths, David and Gang, Haiming and Lazarow, Justin and Kohavi, Gefen and Kang, Kai and Eichner, Marcin and Yang, Yinfei and Dehghan, Afshin and Grasch, Peter}, title = {MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7395-7408} }
CObL: Toward Zero-Shot Ordinal Layering without User Prompting: Aneel Damaraju,

Dean Hazineh,

Todd Zickler; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Damaraju_2025_ICCV, author = {Damaraju, Aneel and Hazineh, Dean and Zickler, Todd}, title = {CObL: Toward Zero-Shot Ordinal Layering without User Prompting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8154-8164} }
Rethinking the Upsampling Process in Light Field Super-Resolution with Spatial-Epipolar Implicit Image Function: Ruixuan Cong,

Yu Wang,

Mingyuan Zhao,

Da Yang,

Rongshan Chen,

Hao Sheng; [pdf] [supp]
[bibtex]
@InProceedings{Cong_2025_ICCV, author = {Cong, Ruixuan and Wang, Yu and Zhao, Mingyuan and Yang, Da and Chen, Rongshan and Sheng, Hao}, title = {Rethinking the Upsampling Process in Light Field Super-Resolution with Spatial-Epipolar Implicit Image Function}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7559-7569} }
SAC-GNC: SAmple Consensus for adaptive Graduated Non-Convexity: Valter Piedade,

Chitturi Sidhartha,

José Gaspar,

Venu Madhav Govindu,

Pedro Miraldo; [pdf] [supp]
[bibtex]
@InProceedings{Piedade_2025_ICCV, author = {Piedade, Valter and Sidhartha, Chitturi and Gaspar, Jos\'e and Govindu, Venu Madhav and Miraldo, Pedro}, title = {SAC-GNC: SAmple Consensus for adaptive Graduated Non-Convexity}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5780-5790} }
VGGSounder: Audio-Visual Evaluations for Foundation Models: Daniil Zverev,

Thaddäus Wiedemer,

Ameya Prabhu,

Matthias Bethge,

Wieland Brendel,

A. Sophia Koepke; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zverev_2025_ICCV, author = {Zverev, Daniil and Wiedemer, Thadd\"aus and Prabhu, Ameya and Bethge, Matthias and Brendel, Wieland and Koepke, A. Sophia}, title = {VGGSounder: Audio-Visual Evaluations for Foundation Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1027-1037} }
SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Models: Xianfu Cheng,

Wei Zhang,

Shiwei Zhang,

Jian Yang,

Xiangyuan Guan,

Xianjie Wu,

Xiang Li,

Ge Zhang,

Jiaheng Liu,

Yuying Mai,

Yutao Zeng,

Zhoufutu Wen,

Ke Jin,

Baorui Wang,

Weixiao Zhou,

Yunhong Lu,

Hangyuan Ji,

Tongliang Li,

Wenhao Huang,

Zhoujun Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2025_ICCV, author = {Cheng, Xianfu and Zhang, Wei and Zhang, Shiwei and Yang, Jian and Guan, Xiangyuan and Wu, Xianjie and Li, Xiang and Zhang, Ge and Liu, Jiaheng and Mai, Yuying and Zeng, Yutao and Wen, Zhoufutu and Jin, Ke and Wang, Baorui and Zhou, Weixiao and Lu, Yunhong and Ji, Hangyuan and Li, Tongliang and Huang, Wenhao and Li, Zhoujun}, title = {SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4637-4646} }
Find a Scapegoat: Poisoning Membership Inference Attack and Defense to Federated Learning: Wenjin Mo,

Zhiyuan Li,

Minghong Fang,

Mingwei Fang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mo_2025_ICCV, author = {Mo, Wenjin and Li, Zhiyuan and Fang, Minghong and Fang, Mingwei}, title = {Find a Scapegoat: Poisoning Membership Inference Attack and Defense to Federated Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3967-3976} }
Generalized Tensor-based Parameter-Efficient Fine-Tuning via Lie Group Transformations: Chongjie Si,

Zhiyi Shi,

Xuehui Wang,

Yichen Xiao,

Xiaokang Yang,

Wei Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Si_2025_ICCV, author = {Si, Chongjie and Shi, Zhiyi and Wang, Xuehui and Xiao, Yichen and Yang, Xiaokang and Shen, Wei}, title = {Generalized Tensor-based Parameter-Efficient Fine-Tuning via Lie Group Transformations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {197-207} }
Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations: Dahee Kwon,

Sehyun Lee,

Jaesik Choi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kwon_2025_ICCV, author = {Kwon, Dahee and Lee, Sehyun and Choi, Jaesik}, title = {Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2356-2365} }
Diversity-Enhanced Distribution Alignment for Dataset Distillation: Hongcheng Li,

Yucan Zhou,

Xiaoyan Gu,

Bo Li,

Weiping Wang; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Hongcheng and Zhou, Yucan and Gu, Xiaoyan and Li, Bo and Wang, Weiping}, title = {Diversity-Enhanced Distribution Alignment for Dataset Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3747-3756} }
Semi-supervised Concept Bottleneck Models: Lijie Hu,

Tianhao Huang,

Huanyi Xie,

Xilin Gong,

Chenyang Ren,

Zhengyu Hu,

Lu Yu,

Ping Ma,

Di Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hu_2025_ICCV, author = {Hu, Lijie and Huang, Tianhao and Xie, Huanyi and Gong, Xilin and Ren, Chenyang and Hu, Zhengyu and Yu, Lu and Ma, Ping and Wang, Di}, title = {Semi-supervised Concept Bottleneck Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2110-2119} }
Can Knowledge be Transferred from Unimodal to Multimodal? Investigating the Transitivity of Multimodal Knowledge Editing: Lingyong Fang,

Xinzhong Wang,

Depeng Wang,

Zongru Wu,

Ya Guo,

Huijia Zhu,

Zhuosheng Zhang,

Gongshen Liu; [pdf] [supp]
[bibtex]
@InProceedings{Fang_2025_ICCV, author = {Fang, Lingyong and Wang, Xinzhong and Wang, Depeng and Wu, Zongru and Guo, Ya and Zhu, Huijia and Zhang, Zhuosheng and Liu, Gongshen}, title = {Can Knowledge be Transferred from Unimodal to Multimodal? Investigating the Transitivity of Multimodal Knowledge Editing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2482-2490} }
GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scene: Xiao Chen,

Tai Wang,

Quanyi Li,

Tao Huang,

Jiangmiao Pang,

Tianfan Xue; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Xiao and Wang, Tai and Li, Quanyi and Huang, Tao and Pang, Jiangmiao and Xue, Tianfan}, title = {GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scene}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5558-5568} }
DialNav: Multi-turn Dialog Navigation with a Remote Guide: Leekyeung Han,

Hyunji Min,

Gyeom Hwangbo,

Jonghyun Choi,

Paul Hongsuck Seo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2025_ICCV, author = {Han, Leekyeung and Min, Hyunji and Hwangbo, Gyeom and Choi, Jonghyun and Seo, Paul Hongsuck}, title = {DialNav: Multi-turn Dialog Navigation with a Remote Guide}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8514-8523} }
VLDrive: Vision-Augmented Lightweight MLLMs for Efficient Language-grounded Autonomous Driving: Ruifei Zhang,

Wei Zhang,

Xiao Tan,

Sibei Yang,

Xiang Wan,

Xiaonan Luo,

Guanbin Li; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Ruifei and Zhang, Wei and Tan, Xiao and Yang, Sibei and Wan, Xiang and Luo, Xiaonan and Li, Guanbin}, title = {VLDrive: Vision-Augmented Lightweight MLLMs for Efficient Language-grounded Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5923-5933} }
Princeton365: A Diverse Dataset with Accurate Camera Pose: Karhan Kayan,

Stamatis Alexandropoulos,

Rishabh Jain,

Yiming Zuo,

Erich Liang,

Jia Deng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kayan_2025_ICCV, author = {Kayan, Karhan and Alexandropoulos, Stamatis and Jain, Rishabh and Zuo, Yiming and Liang, Erich and Deng, Jia}, title = {Princeton365: A Diverse Dataset with Accurate Camera Pose}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7645-7654} }
EFTViT: Efficient Federated Training of Vision Transformers with Masked Images on Resource-Constrained Clients: Meihan Wu,

Tao Chang,

Cui Miao,

Jie Zhou,

Chun Li,

Xiangyu Xu,

Ming Li,

Xiaodong Wang; [pdf] [arXiv]
[bibtex]
@InProceedings{Wu_2025_ICCV, author = {Wu, Meihan and Chang, Tao and Miao, Cui and Zhou, Jie and Li, Chun and Xu, Xiangyu and Li, Ming and Wang, Xiaodong}, title = {EFTViT: Efficient Federated Training of Vision Transformers with Masked Images on Resource-Constrained Clients}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1815-1824} }
A Structure-aware and Motion-adaptive Framework for 3D Human Pose Estimation with Mamba: Ye Lu,

Jie Wang,

Jianjun Gao,

Rui Gong,

Chen Cai,

Kim-Hui Yap; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2025_ICCV, author = {Lu, Ye and Wang, Jie and Gao, Jianjun and Gong, Rui and Cai, Chen and Yap, Kim-Hui}, title = {A Structure-aware and Motion-adaptive Framework for 3D Human Pose Estimation with Mamba}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7958-7968} }
SAFER: Sharpness Aware layer-selective Finetuning for Enhanced Robustness in vision transformers: Bhavna Gopal,

Huanrui Yang,

Mark Horton,

Yiran Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gopal_2025_ICCV, author = {Gopal, Bhavna and Yang, Huanrui and Horton, Mark and Chen, Yiran}, title = {SAFER: Sharpness Aware layer-selective Finetuning for Enhanced Robustness in vision transformers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3999-4008} }
ClearSight: Human Vision-Inspired Solutions for Event-Based Motion Deblurring: Xiaopeng Lin,

Yulong Huang,

Hongwei Ren,

Zunchang Liu,

Hongxiang Huang,

Yue Zhou,

Haotian Fu,

Bojun Cheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2025_ICCV, author = {Lin, Xiaopeng and Huang, Yulong and Ren, Hongwei and Liu, Zunchang and Huang, Hongxiang and Zhou, Yue and Fu, Haotian and Cheng, Bojun}, title = {ClearSight: Human Vision-Inspired Solutions for Event-Based Motion Deblurring}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7462-7471} }
Event-aided Dense and Continuous Point Tracking: Everywhere and Anytime: Zhexiong Wan,

Jianqin Luo,

Yuchao Dai,

Gim Hee Lee; [pdf] [supp]
[bibtex]
@InProceedings{Wan_2025_ICCV, author = {Wan, Zhexiong and Luo, Jianqin and Dai, Yuchao and Lee, Gim Hee}, title = {Event-aided Dense and Continuous Point Tracking: Everywhere and Anytime}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7936-7946} }
Stable-Sim2Real: Exploring Simulation of Real-Captured 3D Data with Two-Stage Depth Diffusion: Mutian Xu,

Chongjie Ye,

Haolin Liu,

Yushuang Wu,

Jiahao Chang,

Xiaoguang Han; [pdf] [supp]
[bibtex]
@InProceedings{Xu_2025_ICCV, author = {Xu, Mutian and Ye, Chongjie and Liu, Haolin and Wu, Yushuang and Chang, Jiahao and Han, Xiaoguang}, title = {Stable-Sim2Real: Exploring Simulation of Real-Captured 3D Data with Two-Stage Depth Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2609-2619} }
Towards Real Unsupervised Anomaly Detection Via Confident Meta-Learning: Muhammad Aqeel,

Shakiba Sharifi,

Marco Cristani,

Francesco Setti; [pdf] [arXiv]
[bibtex]
@InProceedings{Aqeel_2025_ICCV, author = {Aqeel, Muhammad and Sharifi, Shakiba and Cristani, Marco and Setti, Francesco}, title = {Towards Real Unsupervised Anomaly Detection Via Confident Meta-Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4858-4867} }
Efficient Event Camera Data Pretraining with Adaptive Prompt Fusion: Quanmin Liang,

Qiang Li,

Shuai Liu,

Xinzi Cao,

Jinyi Lu,

Feidiao Yang,

Wei Zhang,

Kai Huang,

Yonghong Tian; [pdf] [supp]
[bibtex]
@InProceedings{Liang_2025_ICCV, author = {Liang, Quanmin and Li, Qiang and Liu, Shuai and Cao, Xinzi and Lu, Jinyi and Yang, Feidiao and Zhang, Wei and Huang, Kai and Tian, Yonghong}, title = {Efficient Event Camera Data Pretraining with Adaptive Prompt Fusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8656-8667} }
Unsupervised Part Discovery via Descriptor-Based Masked Image Restoration with Optimized Constraints: Jiahao Xia,

Yike Wu,

Wenjian Huang,

Jianguo Zhang,

Jian Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xia_2025_ICCV, author = {Xia, Jiahao and Wu, Yike and Huang, Wenjian and Zhang, Jianguo and Zhang, Jian}, title = {Unsupervised Part Discovery via Descriptor-Based Masked Image Restoration with Optimized Constraints}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8668-8677} }
SPD: Shallow Backdoor Protecting Deep Backdoor Against Backdoor Detection: Shunjie Yuan,

Xinghua Li,

Xuelin Cao,

Haiyan Zhang,

Mengyao Zhu,

Robert H. Deng; [pdf] [supp]
[bibtex]
@InProceedings{Yuan_2025_ICCV, author = {Yuan, Shunjie and Li, Xinghua and Cao, Xuelin and Zhang, Haiyan and Zhu, Mengyao and Deng, Robert H.}, title = {SPD: Shallow Backdoor Protecting Deep Backdoor Against Backdoor Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4029-4038} }
Mamba-3VL: Taming State Space Model for 3D Vision Language Learning: Yuan Wang,

Yuxin Chen,

Zhongang Qi,

Lijun Liu,

Jile Jiao,

Xuetao Feng,

Yujia Liang,

Ying Shan,

Zhipeng Zhang; [pdf]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Yuan and Chen, Yuxin and Qi, Zhongang and Liu, Lijun and Jiao, Jile and Feng, Xuetao and Liang, Yujia and Shan, Ying and Zhang, Zhipeng}, title = {Mamba-3VL: Taming State Space Model for 3D Vision Language Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6273-6283} }
Performing Defocus Deblurring by Modeling its Formation Process: Zhengbo Zhang,

Lin Geng Foo,

Hossein Rahmani,

Jun Liu,

De Wen Soh; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Zhengbo and Foo, Lin Geng and Rahmani, Hossein and Liu, Jun and Soh, De Wen}, title = {Performing Defocus Deblurring by Modeling its Formation Process}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5791-5801} }
Towards Effective Foundation Model Adaptation for Extreme Cross-Domain Few-Shot Learning: Fei Zhou,

Peng Wang,

Lei Zhang,

Wei Wei,

Chen Ding,

Guosheng Lin,

Yanning Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Zhou_2025_ICCV, author = {Zhou, Fei and Wang, Peng and Zhang, Lei and Wei, Wei and Ding, Chen and Lin, Guosheng and Zhang, Yanning}, title = {Towards Effective Foundation Model Adaptation for Extreme Cross-Domain Few-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4582-4593} }
Boosting Class Representation via Semantically Related Instances for Robust Long-Tailed Learning with Noisy Labels: Yuhang Li,

Zhuying Li,

Yuheng Jia; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Yuhang and Li, Zhuying and Jia, Yuheng}, title = {Boosting Class Representation via Semantically Related Instances for Robust Long-Tailed Learning with Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1516-1525} }
You Are Your Own Best Teacher: Achieving Centralized-level Performance in Federated Learning under Heterogeneous and Long-tailed Data: Shanshan Yan,

Zexi Li,

Chao Wu,

Meng Pang,

Yang Lu,

Yan Yan,

Hanzi Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yan_2025_ICCV, author = {Yan, Shanshan and Li, Zexi and Wu, Chao and Pang, Meng and Lu, Yang and Yan, Yan and Wang, Hanzi}, title = {You Are Your Own Best Teacher: Achieving Centralized-level Performance in Federated Learning under Heterogeneous and Long-tailed Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2750-2759} }
StableDepth: Scene-Consistent and Scale-Invariant Monocular Depth: Zheng Zhang,

Lihe Yang,

Tianyu Yang,

Chaohui Yu,

Xiaoyang Guo,

Yixing Lao,

Hengshuang Zhao; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Zheng and Yang, Lihe and Yang, Tianyu and Yu, Chaohui and Guo, Xiaoyang and Lao, Yixing and Zhao, Hengshuang}, title = {StableDepth: Scene-Consistent and Scale-Invariant Monocular Depth}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7069-7078} }
Personalized Federated Learning under Local Supervision: Qiqi Liu,

Jiaqiang Li,

Yuchen Liu,

Yaochu Jin,

Lingjuan Lyu,

Xiaohu Wu,

Han Yu; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2025_ICCV, author = {Liu, Qiqi and Li, Jiaqiang and Liu, Yuchen and Jin, Yaochu and Lyu, Lingjuan and Wu, Xiaohu and Yu, Han}, title = {Personalized Federated Learning under Local Supervision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4069-4079} }
Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation: Zhenhua Ning,

Zhuotao Tian,

Shaoshuai Shi,

Guangming Lu,

Daojing He,

Wenjie Pei,

Li Jiang; [pdf] [arXiv]
[bibtex]
@InProceedings{Ning_2025_ICCV, author = {Ning, Zhenhua and Tian, Zhuotao and Shi, Shaoshuai and Lu, Guangming and He, Daojing and Pei, Wenjie and Jiang, Li}, title = {Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7851-7860} }
Human-in-the-Loop Local Corrections of 3D Scene Layouts via Infilling: Christopher Xie,

Armen Avetisyan,

Henry Howard-Jenkins,

Yawar Siddiqui,

Julian Straub,

Richard Newcombe,

Vasileios Balntas,

Jakob Engel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xie_2025_ICCV, author = {Xie, Christopher and Avetisyan, Armen and Howard-Jenkins, Henry and Siddiqui, Yawar and Straub, Julian and Newcombe, Richard and Balntas, Vasileios and Engel, Jakob}, title = {Human-in-the-Loop Local Corrections of 3D Scene Layouts via Infilling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5657-5666} }
Fast Globally Optimal and Geometrically Consistent 3D Shape Matching: Paul Roetzer,

Florian Bernard; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Roetzer_2025_ICCV, author = {Roetzer, Paul and Bernard, Florian}, title = {Fast Globally Optimal and Geometrically Consistent 3D Shape Matching}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {912-922} }
EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis: Alexander Mai,

Peter Hedman,

George Kopanas,

Dor Verbin,

David Futschik,

Qiangeng Xu,

Falko Kuester,

Jonathan T. Barron,

Yinda Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mai_2025_ICCV, author = {Mai, Alexander and Hedman, Peter and Kopanas, George and Verbin, Dor and Futschik, David and Xu, Qiangeng and Kuester, Falko and Barron, Jonathan T. and Zhang, Yinda}, title = {EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4930-4939} }
Dissecting Generalized Category Discovery: Multiplex Consensus under Self-Deconstruction: Luyao Tang,

Kunze Huang,

Chaoqi Chen,

Yuxuan Yuan,

Chenxin Li,

Xiaotong Tu,

Xinghao Ding,

Yue Huang; [pdf] [arXiv]
[bibtex]
@InProceedings{Tang_2025_ICCV, author = {Tang, Luyao and Huang, Kunze and Chen, Chaoqi and Yuan, Yuxuan and Li, Chenxin and Tu, Xiaotong and Ding, Xinghao and Huang, Yue}, title = {Dissecting Generalized Category Discovery: Multiplex Consensus under Self-Deconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {297-307} }
Divide-and-Conquer for Enhancing Unlabeled Learning, Stability, and Plasticity in Semi-supervised Continual Learning: Yue Duan,

Taicai Chen,

Lei Qi,

Yinghuan Shi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Duan_2025_ICCV, author = {Duan, Yue and Chen, Taicai and Qi, Lei and Shi, Yinghuan}, title = {Divide-and-Conquer for Enhancing Unlabeled Learning, Stability, and Plasticity in Semi-supervised Continual Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {583-593} }
CogNav: Cognitive Process Modeling for Object Goal Navigation with LLMs: Yihan Cao,

Jiazhao Zhang,

Zhinan Yu,

Shuzhen Liu,

Zheng Qin,

Qin Zou,

Bo Du,

Kai Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2025_ICCV, author = {Cao, Yihan and Zhang, Jiazhao and Yu, Zhinan and Liu, Shuzhen and Qin, Zheng and Zou, Qin and Du, Bo and Xu, Kai}, title = {CogNav: Cognitive Process Modeling for Object Goal Navigation with LLMs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9550-9560} }
Verbalized Representation Learning for Interpretable Few-Shot Generalization: Cheng-Fu Yang,

Da Yin,

Wenbo Hu,

Heng Ji,

Nanyun Peng,

Bolei Zhou,

Kai-Wei Chang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Cheng-Fu and Yin, Da and Hu, Wenbo and Ji, Heng and Peng, Nanyun and Zhou, Bolei and Chang, Kai-Wei}, title = {Verbalized Representation Learning for Interpretable Few-Shot Generalization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1602-1612} }
TESPEC: Temporally-Enhanced Self-Supervised Pretraining for Event Cameras: Mohammad Mohammadi,

Ziyi Wu,

Igor Gilitschenski; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mohammadi_2025_ICCV, author = {Mohammadi, Mohammad and Wu, Ziyi and Gilitschenski, Igor}, title = {TESPEC: Temporally-Enhanced Self-Supervised Pretraining for Event Cameras}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7782-7793} }
Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion: Aleksandar Jevtić,

Christoph Reich,

Felix Wimbauer,

Oliver Hahn,

Christian Rupprecht,

Stefan Roth,

Daniel Cremers; [pdf] [supp]
[bibtex]
@InProceedings{Jevtic_2025_ICCV, author = {Jevti\'c, Aleksandar and Reich, Christoph and Wimbauer, Felix and Hahn, Oliver and Rupprecht, Christian and Roth, Stefan and Cremers, Daniel}, title = {Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6784-6796} }
Federated Domain Generalization with Domain-specific Soft Prompts Generation: Jianhan Wu,

Xiaoyang Qu,

Zhangcheng Huang,

Jianzong Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2025_ICCV, author = {Wu, Jianhan and Qu, Xiaoyang and Huang, Zhangcheng and Wang, Jianzong}, title = {Federated Domain Generalization with Domain-specific Soft Prompts Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2366-2375} }
PS-Mamba: Spatial-Temporal Graph Mamba for Pose Sequence Refinement: Haoye Dong,

Gim Hee Lee; [pdf] [supp]
[bibtex]
@InProceedings{Dong_2025_ICCV, author = {Dong, Haoye and Lee, Gim Hee}, title = {PS-Mamba: Spatial-Temporal Graph Mamba for Pose Sequence Refinement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8568-8578} }
IRASim: A Fine-Grained World Model for Robot Manipulation: Fangqi Zhu,

Hongtao Wu,

Song Guo,

Yuxiao Liu,

Chilam Cheang,

Tao Kong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2025_ICCV, author = {Zhu, Fangqi and Wu, Hongtao and Guo, Song and Liu, Yuxiao and Cheang, Chilam and Kong, Tao}, title = {IRASim: A Fine-Grained World Model for Robot Manipulation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9834-9844} }
Dataset Distillation as Data Compression: A Rate-Utility Perspective: Youneng Bao,

Yiping Liu,

Zhuo Chen,

Yongsheng Liang,

Mu Li,

Kede Ma; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bao_2025_ICCV, author = {Bao, Youneng and Liu, Yiping and Chen, Zhuo and Liang, Yongsheng and Li, Mu and Ma, Kede}, title = {Dataset Distillation as Data Compression: A Rate-Utility Perspective}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {519-529} }
Consensus-Driven Active Model Selection: Justin Kay,

Grant Van Horn,

Subhransu Maji,

Daniel Sheldon,

Sara Beery; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kay_2025_ICCV, author = {Kay, Justin and Van Horn, Grant and Maji, Subhransu and Sheldon, Daniel and Beery, Sara}, title = {Consensus-Driven Active Model Selection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4594-4604} }
Learning an Implicit Physics Model for Image-based Fluid Simulation: Emily Yue-Ting Jia,

Jiageng Mao,

Zhiyuan Gao,

Yajie Zhao,

Yue Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jia_2025_ICCV, author = {Jia, Emily Yue-Ting and Mao, Jiageng and Gao, Zhiyuan and Zhao, Yajie and Wang, Yue}, title = {Learning an Implicit Physics Model for Image-based Fluid Simulation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7048-7057} }
Task-Decoupled Bezier Surface Constraint for Uneven Low-Light Image Enhancement: Xingxiang Zhou,

Xiangdong Su,

Haoran Zhang,

Wei Chen,

Guanglai Gao; [pdf]
[bibtex]
@InProceedings{Zhou_2025_ICCV, author = {Zhou, Xingxiang and Su, Xiangdong and Zhang, Haoran and Chen, Wei and Gao, Guanglai}, title = {Task-Decoupled Bezier Surface Constraint for Uneven Low-Light Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6859-6868} }
PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection: Mahdiyar Molahasani,

Azadeh Motamedi,

Michael Greenspan,

Il-Min Kim,

Ali Etemad; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Molahasani_2025_ICCV, author = {Molahasani, Mahdiyar and Motamedi, Azadeh and Greenspan, Michael and Kim, Il-Min and Etemad, Ali}, title = {PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {688-697} }
Is Tracking Really More Challenging in First Person Egocentric Vision?: Matteo Dunnhofer,

Zaira Manigrasso,

Christian Micheloni; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dunnhofer_2025_ICCV, author = {Dunnhofer, Matteo and Manigrasso, Zaira and Micheloni, Christian}, title = {Is Tracking Really More Challenging in First Person Egocentric Vision?}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5879-5889} }
TorchAdapt: Towards Light-Agnostic Real-Time Visual Perception: Khurram Azeem Hashmi,

Karthik Palyakere Suresh,

Didier Stricker,

Muhammad Zeshan Afzal; [pdf] [supp]
[bibtex]
@InProceedings{Hashmi_2025_ICCV, author = {Hashmi, Khurram Azeem and Suresh, Karthik Palyakere and Stricker, Didier and Afzal, Muhammad Zeshan}, title = {TorchAdapt: Towards Light-Agnostic Real-Time Visual Perception}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5645-5656} }
VehicleMAE: View-asymmetry Mutual Learning for Vehicle Re-identification Pre-training via Masked AutoEncoders: Qi Wang,

Zeyu Zhang,

Dong Wang,

Di Gai,

Xin Xiong,

Jiyang Xu,

Ruihua Zhou; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Qi and Zhang, Zeyu and Wang, Dong and Gai, Di and Xiong, Xin and Xu, Jiyang and Zhou, Ruihua}, title = {VehicleMAE: View-asymmetry Mutual Learning for Vehicle Re-identification Pre-training via Masked AutoEncoders}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4701-4711} }
RANKCLIP: Ranking-Consistent Language-Image Pretraining: Yiming Zhang,

Zhuokai Zhao,

Zhaorun Chen,

Zhili Feng,

Zenghui Ding,

Yining Sun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Yiming and Zhao, Zhuokai and Chen, Zhaorun and Feng, Zhili and Ding, Zenghui and Sun, Yining}, title = {RANKCLIP: Ranking-Consistent Language-Image Pretraining}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3874-3884} }
Is Visual in-Context Learning for Compositional Medical Tasks within Reach?: Simon Reiß,

Zdravko Marinov,

Alexander Jaus,

Constantin Seibold,

M. Saquib Sarfraz,

Erik Rodner,

Rainer Stiefelhagen; [pdf] [supp]
[bibtex]
@InProceedings{Reiss_2025_ICCV, author = {Rei{\ss}, Simon and Marinov, Zdravko and Jaus, Alexander and Seibold, Constantin and Sarfraz, M. Saquib and Rodner, Erik and Stiefelhagen, Rainer}, title = {Is Visual in-Context Learning for Compositional Medical Tasks within Reach?}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2642-2652} }
Details Matter for Indoor Open-vocabulary 3D Instance Segmentation: Sanghun Jung,

Jingjing Zheng,

Ke Zhang,

Nan Qiao,

Albert Y. C. Chen,

Lu Xia,

Chi Liu,

Yuyin Sun,

Xiao Zeng,

Hsiang-Wei Huang,

Byron Boots,

Min Sun,

Cheng-Hao Kuo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jung_2025_ICCV, author = {Jung, Sanghun and Zheng, Jingjing and Zhang, Ke and Qiao, Nan and Chen, Albert Y. C. and Xia, Lu and Liu, Chi and Sun, Yuyin and Zeng, Xiao and Huang, Hsiang-Wei and Boots, Byron and Sun, Min and Kuo, Cheng-Hao}, title = {Details Matter for Indoor Open-vocabulary 3D Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9627-9637} }
Differentially Private Fine-Tuning of Diffusion Models: Yu-Lin Tsai,

Yizhe Li,

Chia-Mu Yu,

Xuebin Ren,

Po-Yu Chen,

Zekai Chen,

Francois Buet-Golfouse; [pdf] [arXiv]
[bibtex]
@InProceedings{Tsai_2025_ICCV, author = {Tsai, Yu-Lin and Li, Yizhe and Yu, Chia-Mu and Ren, Xuebin and Chen, Po-Yu and Chen, Zekai and Buet-Golfouse, Francois}, title = {Differentially Private Fine-Tuning of Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4561-4571} }
Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility: Melih Barsbey,

Lucas Prieto,

Stefanos Zafeiriou,

Tolga Birdal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Barsbey_2025_ICCV, author = {Barsbey, Melih and Prieto, Lucas and Zafeiriou, Stefanos and Birdal, Tolga}, title = {Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2055-2066} }
TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention: Jinhao Duan,

Fei Kong,

Hao Cheng,

James Diffenderfer,

Bhavya Kailkhura,

Lichao Sun,

Xiaofeng Zhu,

Xiaoshuang Shi,

Kaidi Xu; [pdf] [supp]
[bibtex]
@InProceedings{Duan_2025_ICCV, author = {Duan, Jinhao and Kong, Fei and Cheng, Hao and Diffenderfer, James and Kailkhura, Bhavya and Sun, Lichao and Zhu, Xiaofeng and Shi, Xiaoshuang and Xu, Kaidi}, title = {TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7372-7382} }
Customizing Domain Adapters for Domain Generalization: Yuyang Ji,

Zeyi Huang,

Haohan Wang,

Yong Jae Lee; [pdf] [supp]
[bibtex]
@InProceedings{Ji_2025_ICCV, author = {Ji, Yuyang and Huang, Zeyi and Wang, Haohan and Lee, Yong Jae}, title = {Customizing Domain Adapters for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {934-944} }
Structured Policy Optimization: Enhance Large Vision-Language Model via Self-referenced Dialogue: Guohao Sun,

Can Qin,

Yihao Feng,

Zeyuan Chen,

Ran Xu,

Sohail Dianat,

Majid Rabbani,

Raghuveer Rao,

Zhiqiang Tao; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2025_ICCV, author = {Sun, Guohao and Qin, Can and Feng, Yihao and Chen, Zeyuan and Xu, Ran and Dianat, Sohail and Rabbani, Majid and Rao, Raghuveer and Tao, Zhiqiang}, title = {Structured Policy Optimization: Enhance Large Vision-Language Model via Self-referenced Dialogue}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {741-751} }
UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI: Fangwei Zhong,

Kui Wu,

Churan Wang,

Hao Chen,

Hai Ci,

Zhoujun Li,

Yizhou Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhong_2025_ICCV, author = {Zhong, Fangwei and Wu, Kui and Wang, Churan and Chen, Hao and Ci, Hai and Li, Zhoujun and Wang, Yizhou}, title = {UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5769-5779} }
Deep Space Weather Model: Long-Range Solar Flare Prediction from Multi-Wavelength Images: Shunya Nagashima,

Komei Sugiura; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nagashima_2025_ICCV, author = {Nagashima, Shunya and Sugiura, Komei}, title = {Deep Space Weather Model: Long-Range Solar Flare Prediction from Multi-Wavelength Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9396-9405} }
Zero-Shot Vision Encoder Grafting via LLM Surrogates: Kaiyu Yue,

Vasu Singla,

Menglin Jia,

John Kirchenbauer,

Rifaa Qadri,

Zikui Cai,

Abhinav Bhatele,

Furong Huang,

Tom Goldstein; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yue_2025_ICCV, author = {Yue, Kaiyu and Singla, Vasu and Jia, Menglin and Kirchenbauer, John and Qadri, Rifaa and Cai, Zikui and Bhatele, Abhinav and Huang, Furong and Goldstein, Tom}, title = {Zero-Shot Vision Encoder Grafting via LLM Surrogates}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4275-4284} }
Depth Any Event Stream: Enhancing Event-based Monocular Depth Estimation via Dense-to-Sparse Distillation: Jinjing Zhu,

Tianbo Pan,

Zidong Cao,

Yexin Liu,

James T. Kwok,

Hui Xiong; [pdf]
[bibtex]
@InProceedings{Zhu_2025_ICCV, author = {Zhu, Jinjing and Pan, Tianbo and Cao, Zidong and Liu, Yexin and Kwok, James T. and Xiong, Hui}, title = {Depth Any Event Stream: Enhancing Event-based Monocular Depth Estimation via Dense-to-Sparse Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5146-5155} }
Layer-wise Vision Injection with Disentangled Attention for Efficient LVLMs: Xuange Zhang,

Dengjie Li,

Bo Liu,

Zenghao Bao,

Yao Zhou,

Baisong Yang,

Zhongying Liu,

Yujie Zhong,

Tongtong Yuan; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Xuange and Li, Dengjie and Liu, Bo and Bao, Zenghao and Zhou, Yao and Yang, Baisong and Liu, Zhongying and Zhong, Yujie and Yuan, Tongtong}, title = {Layer-wise Vision Injection with Disentangled Attention for Efficient LVLMs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7004-7013} }
FLSeg: Enhancing Privacy and Robustness in Federated Learning under Heterogeneous Data via Model Segmentation: Zichun Su,

Zhi Lu,

Yutong Wu,

Renfei Shen,

Songfeng Lu; [pdf] [supp]
[bibtex]
@InProceedings{Su_2025_ICCV, author = {Su, Zichun and Lu, Zhi and Wu, Yutong and Shen, Renfei and Lu, Songfeng}, title = {FLSeg: Enhancing Privacy and Robustness in Federated Learning under Heterogeneous Data via Model Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3916-3925} }
Partially Matching Submap Helps: Uncertainty Modeling and Propagation for Text to Point Cloud Localization: Mingtao Feng,

Longlong Mei,

Zijie Wu,

Jianqiao Luo,

Fenghao Tian,

Jie Feng,

Weisheng Dong,

Yaonan Wang; [pdf] [supp]
[bibtex]
@InProceedings{Feng_2025_ICCV, author = {Feng, Mingtao and Mei, Longlong and Wu, Zijie and Luo, Jianqiao and Tian, Fenghao and Feng, Jie and Dong, Weisheng and Wang, Yaonan}, title = {Partially Matching Submap Helps: Uncertainty Modeling and Propagation for Text to Point Cloud Localization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8296-8305} }
Adapting Vehicle Detectors for Aerial Imagery to Unseen Domains with Weak Supervision: Xiao Fang,

Minhyek Jeon,

Zheyang Qin,

Stanislav Panev,

Celso De Melo,

Shuowen Hu,

Shayok Chakraborty,

Fernando De La Torre; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fang_2025_ICCV, author = {Fang, Xiao and Jeon, Minhyek and Qin, Zheyang and Panev, Stanislav and De Melo, Celso and Hu, Shuowen and Chakraborty, Shayok and De La Torre, Fernando}, title = {Adapting Vehicle Detectors for Aerial Imagery to Unseen Domains with Weak Supervision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8088-8099} }
3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark: Wufei Ma,

Haoyu Chen,

Guofeng Zhang,

Yu-Cheng Chou,

Jieneng Chen,

Celso de Melo,

Alan Yuille; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2025_ICCV, author = {Ma, Wufei and Chen, Haoyu and Zhang, Guofeng and Chou, Yu-Cheng and Chen, Jieneng and de Melo, Celso and Yuille, Alan}, title = {3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6924-6934} }
Causality-guided Prompt Learning for Vision-language Models via Visual Granulation: Mengyu Gao,

Qiulei Dong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2025_ICCV, author = {Gao, Mengyu and Dong, Qiulei}, title = {Causality-guided Prompt Learning for Vision-language Models via Visual Granulation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1141-1151} }
Arti-PG: A Toolbox for Procedurally Synthesizing Large-Scale and Diverse Articulated Objects with Rich Annotations: Jianhua Sun,

Yuxuan Li,

Jiude Wei,

Longfei Xu,

Nange Wang,

Yining Zhang,

Cewu Lu; [pdf]
[bibtex]
@InProceedings{Sun_2025_ICCV, author = {Sun, Jianhua and Li, Yuxuan and Wei, Jiude and Xu, Longfei and Wang, Nange and Zhang, Yining and Lu, Cewu}, title = {Arti-PG: A Toolbox for Procedurally Synthesizing Large-Scale and Diverse Articulated Objects with Rich Annotations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6396-6405} }
One Last Attention for Your Vision-Language Model: Liang Chen,

Ghazi Shazan Ahmad,

Tianjun Yao,

Lingqiao Liu,

Zhiqiang Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Liang and Ahmad, Ghazi Shazan and Yao, Tianjun and Liu, Lingqiao and Shen, Zhiqiang}, title = {One Last Attention for Your Vision-Language Model}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1464-1473} }
MMCR: Benchmarking Cross-Source Reasoning in Scientific Papers: Yang Tian,

Zheng Lu,

Mingqi Gao,

Zheng Liu,

Bo Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tian_2025_ICCV, author = {Tian, Yang and Lu, Zheng and Gao, Mingqi and Liu, Zheng and Zhao, Bo}, title = {MMCR: Benchmarking Cross-Source Reasoning in Scientific Papers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {488-497} }
Entropy-Adaptive Diffusion Policy Optimization with Dynamic Step Alignment: RenYe Yan,

Jikang Cheng,

Yaozhong Gan,

Shikun Sun,

You Wu,

Yunfan Yang,

Liang Ling,

Jinlong Lin,

Yeshuang Zhu,

Jie Zhou,

Jinchao Zhang,

Junliang Xing,

Yimao Cai,

Ru Huang; [pdf] [supp]
[bibtex]
@InProceedings{Yan_2025_ICCV, author = {Yan, RenYe and Cheng, Jikang and Gan, Yaozhong and Sun, Shikun and Wu, You and Yang, Yunfan and Ling, Liang and Lin, Jinlong and Zhu, Yeshuang and Zhou, Jie and Zhang, Jinchao and Xing, Junliang and Cai, Yimao and Huang, Ru}, title = {Entropy-Adaptive Diffusion Policy Optimization with Dynamic Step Alignment}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1924-1934} }
Bokehlicious: Photorealistic Bokeh Rendering with Controllable Apertures: Tim Seizinger,

Florin-Alexandru Vasluianu,

Marcos V. Conde,

Zongwei Wu,

Radu Timofte; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Seizinger_2025_ICCV, author = {Seizinger, Tim and Vasluianu, Florin-Alexandru and Conde, Marcos V. and Wu, Zongwei and Timofte, Radu}, title = {Bokehlicious: Photorealistic Bokeh Rendering with Controllable Apertures}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8908-8917} }
MMAT-1M: A Large Reasoning Dataset for Multimodal Agent Tuning: Tianhong Gao,

Yannian Fu,

Weiqun Wu,

Haixiao Yue,

Shanshan Liu,

Gang Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Gao_2025_ICCV, author = {Gao, Tianhong and Fu, Yannian and Wu, Weiqun and Yue, Haixiao and Liu, Shanshan and Zhang, Gang}, title = {MMAT-1M: A Large Reasoning Dataset for Multimodal Agent Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1484-1494} }
Teaching VLMs to Localize Specific Objects from In-context Examples: Sivan Doveh,

Nimrod Shabtay,

Eli Schwartz,

Hilde Kuehne,

Raja Giryes,

Rogerio Feris,

Leonid Karlinsky,

James Glass,

Assaf Arbelle,

Shimon Ullman,

M. Jehanzeb Mirza; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Doveh_2025_ICCV, author = {Doveh, Sivan and Shabtay, Nimrod and Schwartz, Eli and Kuehne, Hilde and Giryes, Raja and Feris, Rogerio and Karlinsky, Leonid and Glass, James and Arbelle, Assaf and Ullman, Shimon and Mirza, M. Jehanzeb}, title = {Teaching VLMs to Localize Specific Objects from In-context Examples}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9572-9582} }
A Hidden Stumbling Block in Generalized Category Discovery: Distracted Attention: Qiyu Xu,

Zhanxuan Hu,

Yu Duan,

Ercheng Pei,

Yonghang Tai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2025_ICCV, author = {Xu, Qiyu and Hu, Zhanxuan and Duan, Yu and Pei, Ercheng and Tai, Yonghang}, title = {A Hidden Stumbling Block in Generalized Category Discovery: Distracted Attention}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {405-414} }
Efficient Unsupervised Shortcut Learning Detection and Mitigation in Transformers: Lukas Kuhn,

Sari Sadiya,

Jörg Schlötterer,

Florian Buettner,

Christin Seifert,

Gemma Roig; [pdf] [supp]
[bibtex]
@InProceedings{Kuhn_2025_ICCV, author = {Kuhn, Lukas and Sadiya, Sari and Schl\"otterer, J\"org and Buettner, Florian and Seifert, Christin and Roig, Gemma}, title = {Efficient Unsupervised Shortcut Learning Detection and Mitigation in Transformers}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2217-2226} }
St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World: Haiwen Feng,

Junyi Zhang,

Qianqian Wang,

Yufei Ye,

Pengcheng Yu,

Michael J. Black,

Trevor Darrell,

Angjoo Kanazawa; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Feng_2025_ICCV, author = {Feng, Haiwen and Zhang, Junyi and Wang, Qianqian and Ye, Yufei and Yu, Pengcheng and Black, Michael J. and Darrell, Trevor and Kanazawa, Angjoo}, title = {St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8503-8513} }
Exploiting Frequency Dynamics for Enhanced Multimodal Event-based Action Recognition: Meiqi Cao,

Xiangbo Shu,

Xin Jiang,

Rui Yan,

Yazhou Yao,

Jinhui Tang; [pdf]
[bibtex]
@InProceedings{Cao_2025_ICCV, author = {Cao, Meiqi and Shu, Xiangbo and Jiang, Xin and Yan, Rui and Yao, Yazhou and Tang, Jinhui}, title = {Exploiting Frequency Dynamics for Enhanced Multimodal Event-based Action Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5969-5979} }
AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations: Junli Liu,

Qizhi Chen,

Zhigang Wang,

Yiwen Tang,

Yiting Zhang,

Chi Yan,

Dong Wang,

Xuelong Li,

Bin Zhao; [pdf] [arXiv]
[bibtex]
@InProceedings{Liu_2025_ICCV, author = {Liu, Junli and Chen, Qizhi and Wang, Zhigang and Tang, Yiwen and Zhang, Yiting and Yan, Chi and Wang, Dong and Li, Xuelong and Zhao, Bin}, title = {AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5177-5187} }
DALIP: Distribution Alignment-based Language-Image Pre-Training for Domain-Specific Data: Junjie Wu,

Jiangtao Xie,

Zhaolin Zhang,

Qilong Wang,

Qinghua Hu,

Peihua Li,

Sen Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2025_ICCV, author = {Wu, Junjie and Xie, Jiangtao and Zhang, Zhaolin and Wang, Qilong and Hu, Qinghua and Li, Peihua and Xu, Sen}, title = {DALIP: Distribution Alignment-based Language-Image Pre-Training for Domain-Specific Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2099-2109} }
AGO: Adaptive Grounding for Open World 3D Occupancy Prediction: Peizheng Li,

Shuxiao Ding,

You Zhou,

Qingwen Zhang,

Onat Inak,

Larissa Triess,

Niklas Hanselmann,

Marius Cordts,

Andreas Zell; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Peizheng and Ding, Shuxiao and Zhou, You and Zhang, Qingwen and Inak, Onat and Triess, Larissa and Hanselmann, Niklas and Cordts, Marius and Zell, Andreas}, title = {AGO: Adaptive Grounding for Open World 3D Occupancy Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8645-8655} }
Harnessing Uncertainty-aware Bounding Boxes for Unsupervised 3D Object Detection: Ruiyang Zhang,

Hu Zhang,

Zhedong Zheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Ruiyang and Zhang, Hu and Zheng, Zhedong}, title = {Harnessing Uncertainty-aware Bounding Boxes for Unsupervised 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9230-9240} }
One Encoder to Rule them All: Representation Learning for Model-free Visual Reinforcement Learning using Fourier Neural Operators: Parag Dutta,

Mohd Ayyoob,

Shalabh Bhatnagar,

Ambedkar Dukkipati; [pdf]
[bibtex]
@InProceedings{Dutta_2025_ICCV, author = {Dutta, Parag and Ayyoob, Mohd and Bhatnagar, Shalabh and Dukkipati, Ambedkar}, title = {One Encoder to Rule them All: Representation Learning for Model-free Visual Reinforcement Learning using Fourier Neural Operators}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4818-4827} }
DuCos: Duality Constrained Depth Super-Resolution via Foundation Model: Zhiqiang Yan,

Zhengxue Wang,

Haoye Dong,

Jun Li,

Jian Yang,

Gim Hee Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yan_2025_ICCV, author = {Yan, Zhiqiang and Wang, Zhengxue and Dong, Haoye and Li, Jun and Yang, Jian and Lee, Gim Hee}, title = {DuCos: Duality Constrained Depth Super-Resolution via Foundation Model}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8361-8371} }
PBFG: A New Physically-Based Dataset and Removal of Lens Flares and Glares: Jie Zhu,

Sungkil Lee; [pdf] [supp]
[bibtex]
@InProceedings{Zhu_2025_ICCV, author = {Zhu, Jie and Lee, Sungkil}, title = {PBFG: A New Physically-Based Dataset and Removal of Lens Flares and Glares}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5448-5457} }
Active Perception Meets Rule-Guided RL: A Two-Phase Approach for Precise Object Navigation in Complex Environments: Liang Qin,

Min Wang,

Peiwei Li,

Wengang Zhou,

Houqiang Li; [pdf]
[bibtex]
@InProceedings{Qin_2025_ICCV, author = {Qin, Liang and Wang, Min and Li, Peiwei and Zhou, Wengang and Li, Houqiang}, title = {Active Perception Meets Rule-Guided RL: A Two-Phase Approach for Precise Object Navigation in Complex Environments}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7603-7612} }
CAT: A Unified Click-and-Track Framework for Realistic Tracking: Yongsheng Yuan,

Jie Zhao,

Dong Wang,

Huchuan Lu; [pdf]
[bibtex]
@InProceedings{Yuan_2025_ICCV, author = {Yuan, Yongsheng and Zhao, Jie and Wang, Dong and Lu, Huchuan}, title = {CAT: A Unified Click-and-Track Framework for Realistic Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5690-5700} }
Differential-informed Sample Selection Accelerates Multimodal Contrastive Learning: Zihua Zhao,

Feng Hong,

Mengxi Chen,

Pengyi Chen,

Benyuan Liu,

Jiangchao Yao,

Ya Zhang,

Yanfeng Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2025_ICCV, author = {Zhao, Zihua and Hong, Feng and Chen, Mengxi and Chen, Pengyi and Liu, Benyuan and Yao, Jiangchao and Zhang, Ya and Wang, Yanfeng}, title = {Differential-informed Sample Selection Accelerates Multimodal Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2930-2940} }
Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space: Yingping Liang,

Yutao Hu,

Wenqi Shao,

Ying Fu; [pdf] [arXiv]
[bibtex]
@InProceedings{Liang_2025_ICCV, author = {Liang, Yingping and Hu, Yutao and Shao, Wenqi and Fu, Ying}, title = {Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6621-6631} }
GausSim: Foreseeing Reality by Gaussian Simulator for Elastic Objects: Yidi Shao,

Mu Huang,

Chen Change Loy,

Bo Dai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shao_2025_ICCV, author = {Shao, Yidi and Huang, Mu and Loy, Chen Change and Dai, Bo}, title = {GausSim: Foreseeing Reality by Gaussian Simulator for Elastic Objects}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7841-7850} }
HOLa: Zero-Shot HOI Detection with Low-Rank Decomposed VLM Feature Adaptation: Qinqian Lei,

Bo Wang,

Robby T. Tan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lei_2025_ICCV, author = {Lei, Qinqian and Wang, Bo and Tan, Robby T.}, title = {HOLa: Zero-Shot HOI Detection with Low-Rank Decomposed VLM Feature Adaptation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1825-1835} }
DiffRefine: Diffusion-based Proposal Specific Point Cloud Densification for Cross-Domain Object Detection: Sangyun Shin,

Yuhang He,

Xinyu Hou,

Samuel Hodgson,

Andrew Markham,

Niki Trigoni; [pdf]
[bibtex]
@InProceedings{Shin_2025_ICCV, author = {Shin, Sangyun and He, Yuhang and Hou, Xinyu and Hodgson, Samuel and Markham, Andrew and Trigoni, Niki}, title = {DiffRefine: Diffusion-based Proposal Specific Point Cloud Densification for Cross-Domain Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4888-4897} }
SMSTracker: Tri-path Score Mask Sigma Fusion for Multi-Modal Tracking: Sixian Chan,

Zedong Li,

Wenhao Li,

Shijian Lu,

Chunhua Shen,

Xiaoqin Zhang; [pdf]
[bibtex]
@InProceedings{Chan_2025_ICCV, author = {Chan, Sixian and Li, Zedong and Li, Wenhao and Lu, Shijian and Shen, Chunhua and Zhang, Xiaoqin}, title = {SMSTracker: Tri-path Score Mask Sigma Fusion for Multi-Modal Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4766-4775} }
Aligning Constraint Generation with Design Intent in Parametric CAD: Evan Casey,

Tianyu Zhang,

Shu Ishida,

John Roger Thompson,

Amir Khasahmadi,

Joseph George Lambourne,

Pradeep Kumar Jayaraman,

Karl D.D. Willis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Casey_2025_ICCV, author = {Casey, Evan and Zhang, Tianyu and Ishida, Shu and Thompson, John Roger and Khasahmadi, Amir and Lambourne, Joseph George and Jayaraman, Pradeep Kumar and Willis, Karl D.D.}, title = {Aligning Constraint Generation with Design Intent in Parametric CAD}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8613-8622} }
SMP-Attack: Boosting the Transferability of Feature Importance-based Adversarial Attack with Semantics-aware Multi-granularity Patchout: Wen Yang,

Guodong Liu,

Di Ming; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Wen and Liu, Guodong and Ming, Di}, title = {SMP-Attack: Boosting the Transferability of Feature Importance-based Adversarial Attack with Semantics-aware Multi-granularity Patchout}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4444-4454} }
GWM: Towards Scalable Gaussian World Models for Robotic Manipulation: Guanxing Lu,

Baoxiong Jia,

Puhao Li,

Yixin Chen,

Ziwei Wang,

Yansong Tang,

Siyuan Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2025_ICCV, author = {Lu, Guanxing and Jia, Baoxiong and Li, Puhao and Chen, Yixin and Wang, Ziwei and Tang, Yansong and Huang, Siyuan}, title = {GWM: Towards Scalable Gaussian World Models for Robotic Manipulation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9263-9274} }
Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering: Kaixuan Jiang,

Yang Liu,

Weixing Chen,

Jingzhou Luo,

Ziliang Chen,

Ling Pan,

Guanbin Li,

Liang Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2025_ICCV, author = {Jiang, Kaixuan and Liu, Yang and Chen, Weixing and Luo, Jingzhou and Chen, Ziliang and Pan, Ling and Li, Guanbin and Lin, Liang}, title = {Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9091-9101} }
Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens: Qihang Fan,

Huaibo Huang,

Mingrui Chen,

Ran He; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fan_2025_ICCV, author = {Fan, Qihang and Huang, Huaibo and Chen, Mingrui and He, Ran}, title = {Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4019-4028} }
Moderating the Generalization of Score-based Generative Model: Wan Jiang,

He Wang,

Xin Zhang,

Dan Guo,

Zhaoxin Fan,

Yunfeng Diao,

Richang Hong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2025_ICCV, author = {Jiang, Wan and Wang, He and Zhang, Xin and Guo, Dan and Fan, Zhaoxin and Diao, Yunfeng and Hong, Richang}, title = {Moderating the Generalization of Score-based Generative Model}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {360-369} }
DocThinker: Explainable Multimodal Large Language Models with Rule-based Reinforcement Learning for Document Understanding: Wenwen Yu,

Zhibo Yang,

Yuliang Liu,

Xiang Bai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2025_ICCV, author = {Yu, Wenwen and Yang, Zhibo and Liu, Yuliang and Bai, Xiang}, title = {DocThinker: Explainable Multimodal Large Language Models with Rule-based Reinforcement Learning for Document Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {837-847} }
Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy: Yaxin Xiao,

Qingqing Ye,

Li Hu,

Huadi Zheng,

Haibo Hu,

Zi Liang,

Haoyang Li,

Yijie Jiao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiao_2025_ICCV, author = {Xiao, Yaxin and Ye, Qingqing and Hu, Li and Zheng, Huadi and Hu, Haibo and Liang, Zi and Li, Haoyang and Jiao, Yijie}, title = {Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3058-3068} }
POMATO: Marrying Pointmap Matching with Temporal Motions for Dynamic 3D Reconstruction: Songyan Zhang,

Yongtao Ge,

Jinyuan Tian,

Guangkai Xu,

Hao Chen,

Chen Lv,

Chunhua Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Songyan and Ge, Yongtao and Tian, Jinyuan and Xu, Guangkai and Chen, Hao and Lv, Chen and Shen, Chunhua}, title = {POMATO: Marrying Pointmap Matching with Temporal Motions for Dynamic 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5680-5689} }
Learning Large Motion Estimation from Intermediate Representations with a High-Resolution Optical Flow Dataset Featuring Long-Range Dynamic Motion: Hoonhee Cho,

Yuhwan Jeong,

Kuk-Jin Yoon; [pdf] [supp]
[bibtex]
@InProceedings{Cho_2025_ICCV, author = {Cho, Hoonhee and Jeong, Yuhwan and Yoon, Kuk-Jin}, title = {Learning Large Motion Estimation from Intermediate Representations with a High-Resolution Optical Flow Dataset Featuring Long-Range Dynamic Motion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6176-6187} }
Towards Higher Effective Rank in Parameter-Efficient Fine-tuning using Khatri-Rao Product: Paul Albert,

Frederic Z. Zhang,

Hemanth Saratchandran,

Anton van den Hengel,

Ehsan Abbasnejad; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Albert_2025_ICCV, author = {Albert, Paul and Zhang, Frederic Z. and Saratchandran, Hemanth and van den Hengel, Anton and Abbasnejad, Ehsan}, title = {Towards Higher Effective Rank in Parameter-Efficient Fine-tuning using Khatri-Rao Product}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1292-1302} }
More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning: Luong Tran,

Thieu Vo,

Anh Nguyen,

Sang Dinh,

Van Nguyen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tran_2025_ICCV, author = {Tran, Luong and Vo, Thieu and Nguyen, Anh and Dinh, Sang and Nguyen, Van}, title = {More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1349-1358} }
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle: Miroslav Purkrabek,

Jiri Matas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Purkrabek_2025_ICCV, author = {Purkrabek, Miroslav and Matas, Jiri}, title = {Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9004-9013} }
Hierarchical Cross-modal Prompt Learning for Vision-Language Models: Hao Zheng,

Shunzhi Yang,

Zhuoxin He,

Jinfeng Yang,

Zhenhua Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2025_ICCV, author = {Zheng, Hao and Yang, Shunzhi and He, Zhuoxin and Yang, Jinfeng and Huang, Zhenhua}, title = {Hierarchical Cross-modal Prompt Learning for Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1891-1901} }
RIPE: Reinforcement Learning on Unlabeled Image Pairs for Robust Keypoint Extraction: Johannes Künzel,

Anna Hilsmann,

Peter Eisert; [pdf] [supp]
[bibtex]
@InProceedings{Kunzel_2025_ICCV, author = {K\"unzel, Johannes and Hilsmann, Anna and Eisert, Peter}, title = {RIPE: Reinforcement Learning on Unlabeled Image Pairs for Robust Keypoint Extraction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4868-4877} }
Activation Subspaces for Out-of-Distribution Detection: Barış Zöngür,

Robin Hesse,

Stefan Roth; [pdf] [supp]
[bibtex]
@InProceedings{Zongur_2025_ICCV, author = {Z\"ong\"ur, Bar{\i}\c{s} and Hesse, Robin and Roth, Stefan}, title = {Activation Subspaces for Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3509-3519} }
AllGCD: Leveraging All Unlabeled Data for Generalized Category Discovery: Xinzi Cao,

Ke Chen,

Feidiao Yang,

Xiawu Zheng,

Yonghong Tian,

Yutong Lu; [pdf] [supp]
[bibtex]
@InProceedings{Cao_2025_ICCV, author = {Cao, Xinzi and Chen, Ke and Yang, Feidiao and Zheng, Xiawu and Tian, Yonghong and Lu, Yutong}, title = {AllGCD: Leveraging All Unlabeled Data for Generalized Category Discovery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3293-3303} }
Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability: Boyong He,

Yuxiang Ji,

Zhuoyue Tan,

Liaoni Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{He_2025_ICCV, author = {He, Boyong and Ji, Yuxiang and Tan, Zhuoyue and Wu, Liaoni}, title = {Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1912-1923} }
Power of Cooperative Supervision: Multiple Teachers Framework for Advanced 3D Semi-Supervised Object Detection: Jin-Hee Lee,

Jae-Keun Lee,

Jeseok Kim,

Kwon Soon; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2025_ICCV, author = {Lee, Jin-Hee and Lee, Jae-Keun and Kim, Jeseok and Soon, Kwon}, title = {Power of Cooperative Supervision: Multiple Teachers Framework for Advanced 3D Semi-Supervised Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6994-7003} }
ReassembleNet: Learnable Keypoints and Diffusion for 2D Fresco Reconstruction: Adeela Islam,

Stefano Fiorini,

Stuart James,

Pietro Morerio,

Alessio Del Bue; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Islam_2025_ICCV, author = {Islam, Adeela and Fiorini, Stefano and James, Stuart and Morerio, Pietro and Del Bue, Alessio}, title = {ReassembleNet: Learnable Keypoints and Diffusion for 2D Fresco Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9048-9057} }
Multispectral Demosaicing via Dual Cameras: SaiKiran Tedla,

Junyong Lee,

Beixuan Yang,

Mahmoud Afifi,

Michael S. Brown; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tedla_2025_ICCV, author = {Tedla, SaiKiran and Lee, Junyong and Yang, Beixuan and Afifi, Mahmoud and Brown, Michael S.}, title = {Multispectral Demosaicing via Dual Cameras}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5405-5414} }
TopicGeo: An Efficient Unified Framework for Geolocation: Xin Wang,

Xinlin Wang,

Shuiping Gou; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Xin and Wang, Xinlin and Gou, Shuiping}, title = {TopicGeo: An Efficient Unified Framework for Geolocation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8241-8251} }
Active Learning Meets Foundation Models: Fast Remote Sensing Data Annotation for Object Detection: Marvin Burges,

Philipe Ambrozio Dias,

Carson Woody,

Sarah Walters,

Dalton Lunga; [pdf]
[bibtex]
@InProceedings{Burges_2025_ICCV, author = {Burges, Marvin and Dias, Philipe Ambrozio and Woody, Carson and Walters, Sarah and Lunga, Dalton}, title = {Active Learning Meets Foundation Models: Fast Remote Sensing Data Annotation for Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6058-6068} }
Stronger, Steadier & Superior: Geometric Consistency in Depth VFM Forges Domain Generalized Semantic Segmentation: Siyu Chen,

Ting Han,

Changshe Zhang,

Xin Luo,

Meiliu Wu,

Guorong Cai,

Jinhe Su; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Siyu and Han, Ting and Zhang, Changshe and Luo, Xin and Wu, Meiliu and Cai, Guorong and Su, Jinhe}, title = {Stronger, Steadier \& Superior: Geometric Consistency in Depth VFM Forges Domain Generalized Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8285-8295} }
NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language Models: Sung-Yeon Park,

Can Cui,

Yunsheng Ma,

Ahmadreza Moradipari,

Rohit Gupta,

Kyungtae Han,

Ziran Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2025_ICCV, author = {Park, Sung-Yeon and Cui, Can and Ma, Yunsheng and Moradipari, Ahmadreza and Gupta, Rohit and Han, Kyungtae and Wang, Ziran}, title = {NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8066-8076} }
Mind the Gap: Preserving and Compensating for the Modality Gap in CLIP-Based Continual Learning: Linlan Huang,

Xusheng Cao,

Haori Lu,

Yifan Meng,

Fei Yang,

Xialei Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2025_ICCV, author = {Huang, Linlan and Cao, Xusheng and Lu, Haori and Meng, Yifan and Yang, Fei and Liu, Xialei}, title = {Mind the Gap: Preserving and Compensating for the Modality Gap in CLIP-Based Continual Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3777-3786} }
AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?: Shouwei Ruan,

Hanqing Liu,

Yao Huang,

Xiaoqi Wang,

Caixin Kang,

Hang Su,

Yinpeng Dong,

Xingxing Wei; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ruan_2025_ICCV, author = {Ruan, Shouwei and Liu, Hanqing and Huang, Yao and Wang, Xiaoqi and Kang, Caixin and Su, Hang and Dong, Yinpeng and Wei, Xingxing}, title = {AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7894-7904} }
Not all Views are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation Models: Mateusz Michalkiewicz,

Sheena Bai,

Mahsa Baktashmotlagh,

Varun Jampani,

Guha Balakrishnan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Michalkiewicz_2025_ICCV, author = {Michalkiewicz, Mateusz and Bai, Sheena and Baktashmotlagh, Mahsa and Jampani, Varun and Balakrishnan, Guha}, title = {Not all Views are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9113-9123} }
HumorDB: Can AI understand graphical humor?: Vedaant V Jain,

Gabriel Kreiman,

Felipe dos Santos Alves Feitosa; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jain_2025_ICCV, author = {Jain, Vedaant V and Kreiman, Gabriel and dos Santos Alves Feitosa, Felipe}, title = {HumorDB: Can AI understand graphical humor?}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {604-613} }
PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning: M. Anwar Ma'sum,

Mahardhika Pratama,

Savitha Ramasamy,

Lin Liu,

Habibullah Habibullah,

Ryszard Kowalczyk; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma'sum_2025_ICCV, author = {Ma'sum, M. Anwar and Pratama, Mahardhika and Ramasamy, Savitha and Liu, Lin and Habibullah, Habibullah and Kowalczyk, Ryszard}, title = {PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2471-2481} }
Generalization-Preserved Learning: Closing the Backdoor to Catastrophic Forgetting in Continual Deepfake Detection: Xueyi Zhang,

Peiyin Zhu,

Chengwei Zhang,

Zhiyuan Yan,

Jikang Cheng,

Mingrui Lao,

Siqi Cai,

Yanming Guo; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Xueyi and Zhu, Peiyin and Zhang, Chengwei and Yan, Zhiyuan and Cheng, Jikang and Lao, Mingrui and Cai, Siqi and Guo, Yanming}, title = {Generalization-Preserved Learning: Closing the Backdoor to Catastrophic Forgetting in Continual Deepfake Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3798-3808} }
GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video Diffusion: Gwanghyun Kim,

Xueting Li,

Ye Yuan,

Koki Nagano,

Tianye Li,

Jan Kautz,

Se Young Chun,

Umar Iqbal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2025_ICCV, author = {Kim, Gwanghyun and Li, Xueting and Yuan, Ye and Nagano, Koki and Li, Tianye and Kautz, Jan and Chun, Se Young and Iqbal, Umar}, title = {GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7451-7461} }
GaussianVideo: Efficient Video Representation via Hierarchical Gaussian Splatting: Andrew Bond,

Jui-Hsien Wang,

Long Mai,

Erkut Erdem,

Aykut Erdem; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bond_2025_ICCV, author = {Bond, Andrew and Wang, Jui-Hsien and Mai, Long and Erdem, Erkut and Erdem, Aykut}, title = {GaussianVideo: Efficient Video Representation via Hierarchical Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7187-7196} }
p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay: Jun Zhang,

Desen Meng,

Zhengming Zhang,

Zhenpeng Huang,

Tao Wu,

Limin Wang; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Jun and Meng, Desen and Zhang, Zhengming and Huang, Zhenpeng and Wu, Tao and Wang, Limin}, title = {p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3705-3715} }
SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Experts: Gengze Zhou,

Yicong Hong,

Zun Wang,

Chongyang Zhao,

Mohit Bansal,

Qi Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2025_ICCV, author = {Zhou, Gengze and Hong, Yicong and Wang, Zun and Zhao, Chongyang and Bansal, Mohit and Wu, Qi}, title = {SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Experts}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7794-7807} }
PASD: A Pixel-Adaptive Swarm Dynamics Approach for Unsupervised Low-Light Image Enhancement: Shuai Jin,

Yuhua Qian,

Feijiang Li,

Guoqing Liu,

Xinyan Liang; [pdf]
[bibtex]
@InProceedings{Jin_2025_ICCV, author = {Jin, Shuai and Qian, Yuhua and Li, Feijiang and Liu, Guoqing and Liang, Xinyan}, title = {PASD: A Pixel-Adaptive Swarm Dynamics Approach for Unsupervised Low-Light Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9070-9079} }
ConsNoTrainLoRA: Data-driven Weight Initialization of Low-rank Adapters using Constraints: Debasmit Das,

Hyoungwoo Park,

Munawar Hayat,

Seokeon Choi,

Sungrack Yun,

Fatih Porikli; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Das_2025_ICCV, author = {Das, Debasmit and Park, Hyoungwoo and Hayat, Munawar and Choi, Seokeon and Yun, Sungrack and Porikli, Fatih}, title = {ConsNoTrainLoRA: Data-driven Weight Initialization of Low-rank Adapters using Constraints}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {498-507} }
Adversarial Robustness of Discriminative Self-Supervised Learning in Vision: Ömer Veysel Çağatan,

Ömer Faruk Tal,

M. Emre Gursoy; [pdf] [supp]
[bibtex]
@InProceedings{Cagatan_2025_ICCV, author = {\c{C}a\u{g}atan, \"Omer Veysel and Tal, \"Omer Faruk and Gursoy, M. Emre}, title = {Adversarial Robustness of Discriminative Self-Supervised Learning in Vision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2313-2324} }
Voyaging into Perpetual Dynamic Scenes from a Single View: Fengrui Tian,

Tianjiao Ding,

Jinqi Luo,

Hancheng Min,

Rene Vidal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tian_2025_ICCV, author = {Tian, Fengrui and Ding, Tianjiao and Luo, Jinqi and Min, Hancheng and Vidal, Rene}, title = {Voyaging into Perpetual Dynamic Scenes from a Single View}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7698-7708} }
SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining: Yue Li,

Qi Ma,

Runyi Yang,

Huapeng Li,

Mengjiao Ma,

Bin Ren,

Nikola Popovic,

Nicu Sebe,

Ender Konukoglu,

Theo Gevers,

Luc Van Gool,

Martin R. Oswald,

Danda Pani Paudel; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Yue and Ma, Qi and Yang, Runyi and Li, Huapeng and Ma, Mengjiao and Ren, Bin and Popovic, Nikola and Sebe, Nicu and Konukoglu, Ender and Gevers, Theo and Van Gool, Luc and Oswald, Martin R. and Paudel, Danda Pani}, title = {SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4961-4972} }
Beyond the Limits: Overcoming Negative Correlation of Activation-Based Training-Free NAS: Haidong Kang,

Lianbo Ma,

Pengjun Chen,

Guo Yu,

Xingwei Wang,

Min Huang; [pdf] [supp]
[bibtex]
@InProceedings{Kang_2025_ICCV, author = {Kang, Haidong and Ma, Lianbo and Chen, Pengjun and Yu, Guo and Wang, Xingwei and Huang, Min}, title = {Beyond the Limits: Overcoming Negative Correlation of Activation-Based Training-Free NAS}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {796-805} }
Unknown Text Learning for CLIP-based Few-Shot Open-set Recognition: Rui Ma,

Qilong Wang,

Bing Cao,

Qinghua Hu,

Yahong Han; [pdf] [supp]
[bibtex]
@InProceedings{Ma_2025_ICCV, author = {Ma, Rui and Wang, Qilong and Cao, Bing and Hu, Qinghua and Han, Yahong}, title = {Unknown Text Learning for CLIP-based Few-Shot Open-set Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {657-667} }
VoteSplat: Hough Voting Gaussian Splatting for 3D Scene Understanding: Minchao Jiang,

Shunyu Jia,

Jiaming Gu,

Xiaoyuan Lu,

Guangming Zhu,

Anqi Dong,

Liang Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2025_ICCV, author = {Jiang, Minchao and Jia, Shunyu and Gu, Jiaming and Lu, Xiaoyuan and Zhu, Guangming and Dong, Anqi and Zhang, Liang}, title = {VoteSplat: Hough Voting Gaussian Splatting for 3D Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6456-6465} }
C4D: 4D Made from 3D through Dual Correspondences: Shizun Wang,

Zhenxiang Jiang,

Xingyi Yang,

Xinchao Wang; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Shizun and Jiang, Zhenxiang and Yang, Xingyi and Wang, Xinchao}, title = {C4D: 4D Made from 3D through Dual Correspondences}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7570-7580} }
LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes: Juliette Marrie,

Romain Menegaux,

Michael Arbel,

Diane Larlus,

Julien Mairal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Marrie_2025_ICCV, author = {Marrie, Juliette and Menegaux, Romain and Arbel, Michael and Larlus, Diane and Mairal, Julien}, title = {LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7440-7450} }
PARTE: Part-Guided Texturing for 3D Human Reconstruction from a Single Image: Hyeongjin Nam,

Donghwan Kim,

Gyeongsik Moon,

Kyoung Mu Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nam_2025_ICCV, author = {Nam, Hyeongjin and Kim, Donghwan and Moon, Gyeongsik and Lee, Kyoung Mu}, title = {PARTE: Part-Guided Texturing for 3D Human Reconstruction from a Single Image}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8547-8557} }
3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection: Yung-Hsu Yang,

Luigi Piccinelli,

Mattia Segu,

Siyuan Li,

Rui Huang,

Yuqian Fu,

Marc Pollefeys,

Hermann Blum,

Zuria Bauer; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Yung-Hsu and Piccinelli, Luigi and Segu, Mattia and Li, Siyuan and Huang, Rui and Fu, Yuqian and Pollefeys, Marc and Blum, Hermann and Bauer, Zuria}, title = {3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7429-7439} }
Adversarial Reconstruction Feedback for Robust Fine-grained Generalization: Shijie Wang,

Jian Shi,

Haojie Li; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Shijie and Shi, Jian and Li, Haojie}, title = {Adversarial Reconstruction Feedback for Robust Fine-grained Generalization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3080-3090} }
When Schrodinger Bridge Meets Real-World Image Dehazing with Unpaired Training: Yunwei Lan,

Zhigao Cui,

Xin Luo,

Chang Liu,

Nian Wang,

Menglin Zhang,

Yanzhao Su,

Dong Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lan_2025_ICCV, author = {Lan, Yunwei and Cui, Zhigao and Luo, Xin and Liu, Chang and Wang, Nian and Zhang, Menglin and Su, Yanzhao and Liu, Dong}, title = {When Schrodinger Bridge Meets Real-World Image Dehazing with Unpaired Training}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8756-8765} }
CODE-CL: Conceptor-Based Gradient Projection for Deep Continual Learning: Marco P. E. Apolinario,

Sakshi Choudhary,

Kaushik Roy; [pdf] [supp]
[bibtex]
@InProceedings{Apolinario_2025_ICCV, author = {Apolinario, Marco P. E. and Choudhary, Sakshi and Roy, Kaushik}, title = {CODE-CL: Conceptor-Based Gradient Projection for Deep Continual Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {775-784} }
Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features: Shangbo Wu,

Yu-an Tan,

Ruinan Ma,

Wencong Ma,

Dehua Zhu,

Yuanzhang Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2025_ICCV, author = {Wu, Shangbo and Tan, Yu-an and Ma, Ruinan and Ma, Wencong and Zhu, Dehua and Li, Yuanzhang}, title = {Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {530-540} }
AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMs: Sanjoy Chowdhury,

Sayan Nag,

Subhrajyoti Dasgupta,

Yaoting Wang,

Mohamed Elhoseiny,

Ruohan Gao,

Dinesh Manocha; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chowdhury_2025_ICCV, author = {Chowdhury, Sanjoy and Nag, Sayan and Dasgupta, Subhrajyoti and Wang, Yaoting and Elhoseiny, Mohamed and Gao, Ruohan and Manocha, Dinesh}, title = {AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1590-1601} }
CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos: Nikita Karaev,

Yuri Makarov,

Jianyuan Wang,

Natalia Neverova,

Andrea Vedaldi,

Christian Rupprecht; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Karaev_2025_ICCV, author = {Karaev, Nikita and Makarov, Yuri and Wang, Jianyuan and Neverova, Natalia and Vedaldi, Andrea and Rupprecht, Christian}, title = {CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6013-6022} }
OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations: Peng-Hao Hsu,

Ke Zhang,

Fu-En Wang,

Tao Tu,

Ming-Feng Li,

Yu-Lun Liu,

Albert Y. C. Chen,

Min Sun,

Cheng-Hao Kuo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hsu_2025_ICCV, author = {Hsu, Peng-Hao and Zhang, Ke and Wang, Fu-En and Tu, Tao and Li, Ming-Feng and Liu, Yu-Lun and Chen, Albert Y. C. and Sun, Min and Kuo, Cheng-Hao}, title = {OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8688-8698} }
Benchmarking Multimodal CoT Reward Model Stepwise by Visual Program: Minghe Gao,

Xuqi Liu,

Zhongqi Yue,

Yang Wu,

Shuang Chen,

Juncheng Li,

Siliang Tang,

Fei Wu,

Tat-Seng Chua,

Yueting Zhuang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2025_ICCV, author = {Gao, Minghe and Liu, Xuqi and Yue, Zhongqi and Wu, Yang and Chen, Shuang and Li, Juncheng and Tang, Siliang and Wu, Fei and Chua, Tat-Seng and Zhuang, Yueting}, title = {Benchmarking Multimodal CoT Reward Model Stepwise by Visual Program}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1718-1728} }
Web Artifact Attacks Disrupt Vision Language Models: Maan Qraitem,

Piotr Teterwak,

Kate Saenko,

Bryan A. Plummer; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qraitem_2025_ICCV, author = {Qraitem, Maan and Teterwak, Piotr and Saenko, Kate and Plummer, Bryan A.}, title = {Web Artifact Attacks Disrupt Vision Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1048-1057} }
Quanta Neural Networks: From Photons to Perception: Varun Sundar,

Tianyi Zhang,

Sacha Jungerman,

Mohit Gupta; [pdf] [supp]
[bibtex]
@InProceedings{Sundar_2025_ICCV, author = {Sundar, Varun and Zhang, Tianyi and Jungerman, Sacha and Gupta, Mohit}, title = {Quanta Neural Networks: From Photons to Perception}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5091-5101} }
Beyond RGB: Adaptive Parallel Processing for RAW Object Detection: Shani Gamrian,

Hila Barel,

Feiran Li,

Masakazu Yoshimura,

Daisuke Iso; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gamrian_2025_ICCV, author = {Gamrian, Shani and Barel, Hila and Li, Feiran and Yoshimura, Masakazu and Iso, Daisuke}, title = {Beyond RGB: Adaptive Parallel Processing for RAW Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5547-5557} }
Learning Counterfactually Decoupled Attention for Open-World Model Attribution: Yu Zheng,

Boyang Gong,

Fanye Kong,

Yueqi Duan,

Bingyao Yu,

Wenzhao Zheng,

Lei Chen,

Jiwen Lu,

Jie Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2025_ICCV, author = {Zheng, Yu and Gong, Boyang and Kong, Fanye and Duan, Yueqi and Yu, Bingyao and Zheng, Wenzhao and Chen, Lei and Lu, Jiwen and Zhou, Jie}, title = {Learning Counterfactually Decoupled Attention for Open-World Model Attribution}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {122-132} }
DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion: Qingcheng Zhao,

Xiang Zhang,

Haiyang Xu,

Zeyuan Chen,

Jianwen Xie,

Yuan Gao,

Zhuowen Tu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2025_ICCV, author = {Zhao, Qingcheng and Zhang, Xiang and Xu, Haiyang and Chen, Zeyuan and Xie, Jianwen and Gao, Yuan and Tu, Zhuowen}, title = {DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5722-5733} }
Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens: Suchisrit Gangopadhyay,

Jung-Hee Kim,

Xien Chen,

Patrick Rim,

Hyoungseob Park,

Alex Wong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gangopadhyay_2025_ICCV, author = {Gangopadhyay, Suchisrit and Kim, Jung-Hee and Chen, Xien and Rim, Patrick and Park, Hyoungseob and Wong, Alex}, title = {Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5198-5209} }
FedWSQ: Efficient Federated Learning with Weight Standardization and Distribution-Aware Non-Uniform Quantization: Seung-Wook Kim,

Seongyeol Kim,

Jiah Kim,

Seowon Ji,

Se-Ho Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2025_ICCV, author = {Kim, Seung-Wook and Kim, Seongyeol and Kim, Jiah and Ji, Seowon and Lee, Se-Ho}, title = {FedWSQ: Efficient Federated Learning with Weight Standardization and Distribution-Aware Non-Uniform Quantization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4616-4625} }
Knowledge Transfer from Interaction Learning: Yilin Gao,

Kangyi Chen,

Zhongxing Peng,

Hengjie Lu,

Shugong Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2025_ICCV, author = {Gao, Yilin and Chen, Kangyi and Peng, Zhongxing and Lu, Hengjie and Xu, Shugong}, title = {Knowledge Transfer from Interaction Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3585-3595} }
Dataset Distillation via Vision-Language Category Prototype: Yawen Zou,

Guang Li,

Duo Su,

Zi Wang,

Jun Yu,

Chao Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zou_2025_ICCV, author = {Zou, Yawen and Li, Guang and Su, Duo and Wang, Zi and Yu, Jun and Zhang, Chao}, title = {Dataset Distillation via Vision-Language Category Prototype}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2941-2950} }
Token Activation Map to Visually Explain Multimodal LLMs: Yi Li,

Hualiang Wang,

Xinpeng Ding,

Haonan Wang,

Xiaomeng Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Yi and Wang, Hualiang and Ding, Xinpeng and Wang, Haonan and Li, Xiaomeng}, title = {Token Activation Map to Visually Explain Multimodal LLMs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {48-58} }
A Unified Framework to BRIDGE Complete and Incomplete Deep Multi-View Clustering under Non-IID Missing Patterns: Xiaorui Jiang,

Buyun He,

Peng Yuan Zhou,

Xinyue Chen,

Jingcai Guo,

Jie Xu,

Yong Liao; [pdf] [supp]
[bibtex]
@InProceedings{Jiang_2025_ICCV, author = {Jiang, Xiaorui and He, Buyun and Zhou, Peng Yuan and Chen, Xinyue and Guo, Jingcai and Xu, Jie and Liao, Yong}, title = {A Unified Framework to BRIDGE Complete and Incomplete Deep Multi-View Clustering under Non-IID Missing Patterns}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {594-603} }
PEFTDiff: Diffusion-Guided Transferability Estimation for Parameter-Efficient Fine-Tuning: Prafful Kumar Khoba,

Zijian Wang,

Chetan Arora,

Mahsa Baktashmotlagh; [pdf] [supp]
[bibtex]
@InProceedings{Khoba_2025_ICCV, author = {Khoba, Prafful Kumar and Wang, Zijian and Arora, Chetan and Baktashmotlagh, Mahsa}, title = {PEFTDiff: Diffusion-Guided Transferability Estimation for Parameter-Efficient Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1454-1463} }
Towards Annotation-Free Evaluation: KPAScore for Human Keypoint Detection: Xiaoxiao Wang,

Chunxiao Li,

Peng Sun,

Boming Miao,

Yunjian Zhang,

Yao Zhu; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Xiaoxiao and Li, Chunxiao and Sun, Peng and Miao, Boming and Zhang, Yunjian and Zhu, Yao}, title = {Towards Annotation-Free Evaluation: KPAScore for Human Keypoint Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8441-8450} }
TITAN: Query-Token based Domain Adaptive Adversarial Learning: Tajamul Ashraf,

Janibul Bashir; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ashraf_2025_ICCV, author = {Ashraf, Tajamul and Bashir, Janibul}, title = {TITAN: Query-Token based Domain Adaptive Adversarial Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {250-262} }
AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration: Javier Tirado-Garín,

Javier Civera; [pdf] [supp]
[bibtex]
@InProceedings{Tirado-Garin_2025_ICCV, author = {Tirado-Gar{\'\i}n, Javier and Civera, Javier}, title = {AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8044-8055} }
GEOPARD: Geometric Pretraining for Articulation Prediction in 3D Shapes: Pradyumn Goyal,

Dmitry Petrov,

Sheldon Andrews,

Yizhak Ben-Shabat,

Hsueh-Ti Derek Liu,

Evangelos Kalogerakis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Goyal_2025_ICCV, author = {Goyal, Pradyumn and Petrov, Dmitry and Andrews, Sheldon and Ben-Shabat, Yizhak and Liu, Hsueh-Ti Derek and Kalogerakis, Evangelos}, title = {GEOPARD: Geometric Pretraining for Articulation Prediction in 3D Shapes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9332-9341} }
Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark: Changsheng Gao,

Yifan Ma,

Qiaoxi Chen,

Yenan Xu,

Dong Liu,

Weisi Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2025_ICCV, author = {Gao, Changsheng and Ma, Yifan and Chen, Qiaoxi and Xu, Yenan and Liu, Dong and Lin, Weisi}, title = {Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1068-1077} }
VAGUE: Visual Contexts Clarify Ambiguous Expressions: Heejeong Nam,

Jinwoo Ahn,

Keummin Ka,

Jiwan Chung,

Youngjae Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nam_2025_ICCV, author = {Nam, Heejeong and Ahn, Jinwoo and Ka, Keummin and Chung, Jiwan and Yu, Youngjae}, title = {VAGUE: Visual Contexts Clarify Ambiguous Expressions}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1537-1547} }
Enhancing Numerical Prediction of MLLMs with Soft Labeling: Pei Wang,

Zhaowei Cai,

Hao Yang,

Davide Modolo,

Ashwin Swaminathan; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Pei and Cai, Zhaowei and Yang, Hao and Modolo, Davide and Swaminathan, Ashwin}, title = {Enhancing Numerical Prediction of MLLMs with Soft Labeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3424-3434} }
Open-Unfairness Adversarial Mitigation for Generalized Deepfake Detection: Zhaoyang Li,

Zhu Teng,

Baopeng Zhang,

Jianping Fan; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Zhaoyang and Teng, Zhu and Zhang, Baopeng and Fan, Jianping}, title = {Open-Unfairness Adversarial Mitigation for Generalized Deepfake Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {698-707} }
Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing: Chengxu Liu,

Lu Qi,

Jinshan Pan,

Xueming Qian,

Ming-Hsuan Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2025_ICCV, author = {Liu, Chengxu and Qi, Lu and Pan, Jinshan and Qian, Xueming and Yang, Ming-Hsuan}, title = {Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7538-7547} }
Adversarial Purification via Super-Resolution and Diffusion: Mincheol Park,

Cheonjun Park,

Seungseop Lim,

Mijin Koo,

Hyunwuk Lee,

Won Woo Ro,

Suhyun Kim; [pdf] [supp]
[bibtex]
@InProceedings{Park_2025_ICCV, author = {Park, Mincheol and Park, Cheonjun and Lim, Seungseop and Koo, Mijin and Lee, Hyunwuk and Ro, Won Woo and Kim, Suhyun}, title = {Adversarial Purification via Super-Resolution and Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4605-4615} }
Spatial Alignment and Temporal Matching Adapter for Video-Radar Remote Physiological Measurement: Qian Liang,

Ruixu Geng,

Jinbo Chen,

Haoyu Wang,

Yan Chen,

Yang Hu; [pdf] [supp]
[bibtex]
@InProceedings{Liang_2025_ICCV, author = {Liang, Qian and Geng, Ruixu and Chen, Jinbo and Wang, Haoyu and Chen, Yan and Hu, Yang}, title = {Spatial Alignment and Temporal Matching Adapter for Video-Radar Remote Physiological Measurement}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8623-8633} }
Seal Your Backdoor with Variational Defense: Ivan Sabolić,

Matej Grcić,

Siniša Šegvić; [pdf] [supp]
[bibtex]
@InProceedings{Sabolic_2025_ICCV, author = {Saboli\'c, Ivan and Grci\'c, Matej and \v{S}egvi\'c, Sini\v{s}a}, title = {Seal Your Backdoor with Variational Defense}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {752-764} }
From Abyssal Darkness to Blinding Glare: A Benchmark on Extreme Exposure Correction in Real World: Bo Wang,

Huiyuan Fu,

Zhiye Huang,

Siru Zhang,

Xin Wang,

Huadong Ma; [pdf]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Bo and Fu, Huiyuan and Huang, Zhiye and Zhang, Siru and Wang, Xin and Ma, Huadong}, title = {From Abyssal Darkness to Blinding Glare: A Benchmark on Extreme Exposure Correction in Real World}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7666-7675} }
GeoDiffusion: A Training-Free Framework for Accurate 3D Geometric Conditioning in Image Generation: Phillip Mueller,

Talip Uenlue,

Sebastian Schmidt,

Marcel Kollovieh,

Jiajie Fan,

Stephan Günnemann,

Lars Mikelsons; [pdf] [supp]
[bibtex]
@InProceedings{Mueller_2025_ICCV, author = {Mueller, Phillip and Uenlue, Talip and Schmidt, Sebastian and Kollovieh, Marcel and Fan, Jiajie and G\"unnemann, Stephan and Mikelsons, Lars}, title = {GeoDiffusion: A Training-Free Framework for Accurate 3D Geometric Conditioning in Image Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6374-6384} }
VALLR: Visual ASR Language Model for Lip Reading: Marshall Thomas,

Edward Fish,

Richard Bowden; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Thomas_2025_ICCV, author = {Thomas, Marshall and Fish, Edward and Bowden, Richard}, title = {VALLR: Visual ASR Language Model for Lip Reading}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2846-2856} }
Importance-Based Token Merging for Efficient Image and Video Generation: Haoyu Wu,

Jingyi Xu,

Hieu Le,

Dimitris Samaras; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2025_ICCV, author = {Wu, Haoyu and Xu, Jingyi and Le, Hieu and Samaras, Dimitris}, title = {Importance-Based Token Merging for Efficient Image and Video Generation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4983-4995} }
Semi-ViM: Bidirectional State Space Model for Mitigating Label Imbalance in Semi-Supervised Learning: Hongyang He,

Hongyang Xie,

Haochen You,

Victor Sanchez; [pdf] [supp]
[bibtex]
@InProceedings{He_2025_ICCV, author = {He, Hongyang and Xie, Hongyang and You, Haochen and Sanchez, Victor}, title = {Semi-ViM: Bidirectional State Space Model for Mitigating Label Imbalance in Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {765-774} }
ARMO: Autoregressive Rigging for Multi-Category Objects: Mingze Sun,

Shiwei Mao,

Keyi Chen,

Yurun Chen,

Shunlin Lu,

Jingbo Wang,

Junting Dong,

Ruqi Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2025_ICCV, author = {Sun, Mingze and Mao, Shiwei and Chen, Keyi and Chen, Yurun and Lu, Shunlin and Wang, Jingbo and Dong, Junting and Huang, Ruqi}, title = {ARMO: Autoregressive Rigging for Multi-Category Objects}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7721-7730} }
DIP: Unsupervised Dense In-Context Post-training of Visual Representations: Sophia Sirko-Galouchenko,

Spyros Gidaris,

Antonin Vobecky,

Andrei Bursuc,

Nicolas Thome; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sirko-Galouchenko_2025_ICCV, author = {Sirko-Galouchenko, Sophia and Gidaris, Spyros and Vobecky, Antonin and Bursuc, Andrei and Thome, Nicolas}, title = {DIP: Unsupervised Dense In-Context Post-training of Visual Representations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4264-4274} }
Think Twice: Test-Time Reasoning for Robust CLIP Zero-Shot Classification: Shenyu Lu,

Zhaoying Pan,

Xiaoqian Wang; [pdf] [supp]
[bibtex]
@InProceedings{Lu_2025_ICCV, author = {Lu, Shenyu and Pan, Zhaoying and Wang, Xiaoqian}, title = {Think Twice: Test-Time Reasoning for Robust CLIP Zero-Shot Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2919-2929} }
Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection: Jiasheng Guo,

Xin Gao,

Yuxiang Yan,

Guanghao Li,

Jian Pu; [pdf] [supp]
[bibtex]
@InProceedings{Guo_2025_ICCV, author = {Guo, Jiasheng and Gao, Xin and Yan, Yuxiang and Li, Guanghao and Pu, Jian}, title = {Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9583-9593} }
Environment-Agnostic Pose: Generating Environment-independent Object Representations for 6D Pose Estimation: Shaobo Zhang,

Yuhang Huang,

Wanqing Zhao,

Wei Zhao,

Ziyu Guan,

Jinye Peng; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Shaobo and Huang, Yuhang and Zhao, Wanqing and Zhao, Wei and Guan, Ziyu and Peng, Jinye}, title = {Environment-Agnostic Pose: Generating Environment-independent Object Representations for 6D Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8678-8687} }
Progressive Homeostatic and Plastic Prompt Tuning for Audio-Visual Multi-Task Incremental Learning: Jiong Yin,

Liang Li,

Jiehua Zhang,

Yuhan Gao,

Chenggang Yan,

Xichun Sheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yin_2025_ICCV, author = {Yin, Jiong and Li, Liang and Zhang, Jiehua and Gao, Yuhan and Yan, Chenggang and Sheng, Xichun}, title = {Progressive Homeostatic and Plastic Prompt Tuning for Audio-Visual Multi-Task Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2022-2033} }
DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB Image: Jijun Xiang,

Xuan Zhu,

Xianqi Wang,

Yu Wang,

Hong Zhang,

Fei Guo,

Xin Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiang_2025_ICCV, author = {Xiang, Jijun and Zhu, Xuan and Wang, Xianqi and Wang, Yu and Zhang, Hong and Guo, Fei and Yang, Xin}, title = {DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB Image}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6101-6111} }
Dream-to-Recon: Monocular 3D Reconstruction with Diffusion-Depth Distillation from Single Images: Philipp Wulff,

Felix Wimbauer,

Dominik Muhle,

Daniel Cremers; [pdf] [supp]
[bibtex]
@InProceedings{Wulff_2025_ICCV, author = {Wulff, Philipp and Wimbauer, Felix and Muhle, Dominik and Cremers, Daniel}, title = {Dream-to-Recon: Monocular 3D Reconstruction with Diffusion-Depth Distillation from Single Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9352-9362} }
SplArt: Articulation Estimation and Part-Level Reconstruction with 3D Gaussian Splatting: Shengjie Lin,

Jiading Fang,

Muhammad Zubair Irshad,

Vitor Campagnolo Guizilini,

Rares Andrei Ambrus,

Greg Shakhnarovich,

Matthew R. Walter; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2025_ICCV, author = {Lin, Shengjie and Fang, Jiading and Irshad, Muhammad Zubair and Guizilini, Vitor Campagnolo and Ambrus, Rares Andrei and Shakhnarovich, Greg and Walter, Matthew R.}, title = {SplArt: Articulation Estimation and Part-Level Reconstruction with 3D Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8841-8851} }
FedXDS: Leveraging Model Attribution Methods to counteract Data Heterogeneity in Federated Learning: Maximilian Andreas Hoefler,

Karsten Mueller,

Wojciech Samek; [pdf] [supp]
[bibtex]
@InProceedings{Hoefler_2025_ICCV, author = {Hoefler, Maximilian Andreas and Mueller, Karsten and Samek, Wojciech}, title = {FedXDS: Leveraging Model Attribution Methods to counteract Data Heterogeneity in Federated Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4572-4581} }
Retinex-MEF: Retinex-based Glare Effects Aware Unsupervised Multi-Exposure Image Fusion: Haowen Bai,

Jiangshe Zhang,

Zixiang Zhao,

Lilun Deng,

Yukun Cui,

Shuang Xu; [pdf] [supp]
[bibtex]
@InProceedings{Bai_2025_ICCV, author = {Bai, Haowen and Zhang, Jiangshe and Zhao, Zixiang and Deng, Lilun and Cui, Yukun and Xu, Shuang}, title = {Retinex-MEF: Retinex-based Glare Effects Aware Unsupervised Multi-Exposure Image Fusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7251-7261} }
HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction: Sara Rojas,

Matthieu Armando,

Bernard Ghanem,

Philippe Weinzaepfel,

Vincent Leroy,

Grégory Rogez; [pdf] [supp]
[bibtex]
@InProceedings{Rojas_2025_ICCV, author = {Rojas, Sara and Armando, Matthieu and Ghanem, Bernard and Weinzaepfel, Philippe and Leroy, Vincent and Rogez, Gr\'egory}, title = {HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5027-5037} }
TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models: Mark Yu,

Wenbo Hu,

Jinbo Xing,

Ying Shan; [pdf] [arXiv]
[bibtex]
@InProceedings{Yu_2025_ICCV, author = {Yu, Mark and Hu, Wenbo and Xing, Jinbo and Shan, Ying}, title = {TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {100-111} }
Self-Supervised Monocular 4D Scene Reconstruction for Egocentric Videos: Chengbo Yuan,

Geng Chen,

Li Yi,

Yang Gao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yuan_2025_ICCV, author = {Yuan, Chengbo and Chen, Geng and Yi, Li and Gao, Yang}, title = {Self-Supervised Monocular 4D Scene Reconstruction for Egocentric Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8863-8874} }
CoST: Efficient Collaborative Perception From Unified Spatiotemporal Perspective: Zongheng Tang,

Yi Liu,

Yifan Sun,

Yulu Gao,

Jinyu Chen,

Runsheng Xu,

Si Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tang_2025_ICCV, author = {Tang, Zongheng and Liu, Yi and Sun, Yifan and Gao, Yulu and Chen, Jinyu and Xu, Runsheng and Liu, Si}, title = {CoST: Efficient Collaborative Perception From Unified Spatiotemporal Perspective}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1120-1129} }
Noise-Modeled Diffusion Models for Low-Light Spike Image Restoration: Ruonan Liu,

Lin Zhu,

Xijie Xiang,

Lizhi Wang,

Hua Huang; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2025_ICCV, author = {Liu, Ruonan and Zhu, Lin and Xiang, Xijie and Wang, Lizhi and Huang, Hua}, title = {Noise-Modeled Diffusion Models for Low-Light Spike Image Restoration}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4080-4089} }
Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation: Yusuke Hirota,

Ryo Hachiuma,

Boyi Li,

Ximing Lu,

Michael Ross Boone,

Boris Ivanovic,

Yejin Choi,

Marco Pavone,

Yu-Chiang Frank Wang,

Noa Garcia,

Yuta Nakashima,

Chao-Han Huck Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hirota_2025_ICCV, author = {Hirota, Yusuke and Hachiuma, Ryo and Li, Boyi and Lu, Ximing and Boone, Michael Ross and Ivanovic, Boris and Choi, Yejin and Pavone, Marco and Wang, Yu-Chiang Frank and Garcia, Noa and Nakashima, Yuta and Yang, Chao-Han Huck}, title = {Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8634-8644} }
Learning to Inference Adaptively for Multimodal Large Language Models: Zhuoyan Xu,

Khoi Duc Nguyen,

Preeti Mukherjee,

Saurabh Bagchi,

Somali Chaterji,

Yingyu Liang,

Yin Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2025_ICCV, author = {Xu, Zhuoyan and Nguyen, Khoi Duc and Mukherjee, Preeti and Bagchi, Saurabh and Chaterji, Somali and Liang, Yingyu and Li, Yin}, title = {Learning to Inference Adaptively for Multimodal Large Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3552-3563} }
HazeFlow: Revisit Haze Physical Model as ODE and Non-Homogeneous Haze Generation for Real-World Dehazing: Junseong Shin,

Seungwoo Chung,

Yunjeong Yang,

Tae Hyun Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shin_2025_ICCV, author = {Shin, Junseong and Chung, Seungwoo and Yang, Yunjeong and Kim, Tae Hyun}, title = {HazeFlow: Revisit Haze Physical Model as ODE and Non-Homogeneous Haze Generation for Real-World Dehazing}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6263-6272} }
HoliTracer: Holistic Vectorization of Geographic Objects from Large-Size Remote Sensing Imagery: Yu Wang,

Bo Dang,

Wanchun Li,

Wei Chen,

Yansheng Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Yu and Dang, Bo and Li, Wanchun and Chen, Wei and Li, Yansheng}, title = {HoliTracer: Holistic Vectorization of Geographic Objects from Large-Size Remote Sensing Imagery}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8482-8491} }
Tensor-aggregated LoRA in Federated Fine-tuning: Zhixuan Li,

Binqian Xu,

Xiangbo Shu,

Jiachao Zhang,

Yazhou Yao,

Guo-Sen Xie,

Jinhui Tang; [pdf] [supp]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Zhixuan and Xu, Binqian and Shu, Xiangbo and Zhang, Jiachao and Yao, Yazhou and Xie, Guo-Sen and Tang, Jinhui}, title = {Tensor-aggregated LoRA in Federated Fine-tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1058-1067} }
OVA-Fields: Weakly Supervised Open-Vocabulary Affordance Fields for Robot Operational Part Detection: Heng Su,

Mengying Xie,

Nieqing Cao,

Yan Ding,

Beichen Shao,

Xianlei Long,

Fuqiang Gu,

Chao Chen; [pdf] [supp]
[bibtex]
@InProceedings{Su_2025_ICCV, author = {Su, Heng and Xie, Mengying and Cao, Nieqing and Ding, Yan and Shao, Beichen and Long, Xianlei and Gu, Fuqiang and Chen, Chao}, title = {OVA-Fields: Weakly Supervised Open-Vocabulary Affordance Fields for Robot Operational Part Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6385-6395} }
DiMPLe - Disentangled Multi-Modal Prompt Learning: Enhancing Out-Of-Distribution Alignment with Invariant and Spurious Feature Separation: Umaima Rahman,

Mohammad Yaqub,

Dwarikanath Mahapatra; [pdf] [supp]
[bibtex]
@InProceedings{Rahman_2025_ICCV, author = {Rahman, Umaima and Yaqub, Mohammad and Mahapatra, Dwarikanath}, title = {DiMPLe - Disentangled Multi-Modal Prompt Learning: Enhancing Out-Of-Distribution Alignment with Invariant and Spurious Feature Separation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1634-1643} }
X-Capture: An Open-Source Portable Device for Multi-Sensory Learning: Samuel Clarke,

Suzannah Wistreich,

Yanjie Ze,

Jiajun Wu; [pdf] [supp]
[bibtex]
@InProceedings{Clarke_2025_ICCV, author = {Clarke, Samuel and Wistreich, Suzannah and Ze, Yanjie and Wu, Jiajun}, title = {X-Capture: An Open-Source Portable Device for Multi-Sensory Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6436-6446} }
UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence: Jie Feng,

Shengyuan Wang,

Tianhui Liu,

Yanxin Xi,

Yong Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Feng_2025_ICCV, author = {Feng, Jie and Wang, Shengyuan and Liu, Tianhui and Xi, Yanxin and Li, Yong}, title = {UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6209-6219} }
VLM4D: Towards Spatiotemporal Awareness in Vision Language Models: Shijie Zhou,

Alexander Vilesov,

Xuehai He,

Ziyu Wan,

Shuwang Zhang,

Aditya Nagachandra,

Di Chang,

Dongdong Chen,

Xin Eric Wang,

Achuta Kadambi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2025_ICCV, author = {Zhou, Shijie and Vilesov, Alexander and He, Xuehai and Wan, Ziyu and Zhang, Shuwang and Nagachandra, Aditya and Chang, Di and Chen, Dongdong and Wang, Xin Eric and Kadambi, Achuta}, title = {VLM4D: Towards Spatiotemporal Awareness in Vision Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8600-8612} }
Multimodal LLM Guided Exploration and Active Mapping using Fisher Information: Wen Jiang,

Boshu Lei,

Katrina Ashton,

Kostas Daniilidis; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2025_ICCV, author = {Jiang, Wen and Lei, Boshu and Ashton, Katrina and Daniilidis, Kostas}, title = {Multimodal LLM Guided Exploration and Active Mapping using Fisher Information}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5392-5404} }
X-Fusion: Introducing New Modality to Frozen Large Language Models: Sicheng Mo,

Thao Nguyen,

Xun Huang,

Siddharth Srinivasan Iyer,

Yijun Li,

Yuchen Liu,

Abhishek Tandon,

Eli Shechtman,

Krishna Kumar Singh,

Yong Jae Lee,

Bolei Zhou,

Yuheng Li; [pdf] [supp]
[bibtex]
@InProceedings{Mo_2025_ICCV, author = {Mo, Sicheng and Nguyen, Thao and Huang, Xun and Iyer, Siddharth Srinivasan and Li, Yijun and Liu, Yuchen and Tandon, Abhishek and Shechtman, Eli and Singh, Krishna Kumar and Lee, Yong Jae and Zhou, Bolei and Li, Yuheng}, title = {X-Fusion: Introducing New Modality to Frozen Large Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {228-238} }
KOEnsAttack: Towards Efficient Data-Free Black-Box Adversarial Attacks via Knowledge-Orthogonalized Substitute Ensembles: Chaoyong Yang,

Jia-Li Yin,

Bin Chen,

Zhaozhe Hu,

Xiaolei Liu,

Wei Lin; [pdf]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Chaoyong and Yin, Jia-Li and Chen, Bin and Hu, Zhaozhe and Liu, Xiaolei and Lin, Wei}, title = {KOEnsAttack: Towards Efficient Data-Free Black-Box Adversarial Attacks via Knowledge-Orthogonalized Substitute Ensembles}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3101-3110} }
Multimodal Large Language Model-Guided ISP Hyperparameter Optimization with Dynamic Preference Learning: Xinyu Sun,

Zhikun Zhao,

Congyan Lang,

Bing Li,

Juan Wang; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2025_ICCV, author = {Sun, Xinyu and Zhao, Zhikun and Lang, Congyan and Li, Bing and Wang, Juan}, title = {Multimodal Large Language Model-Guided ISP Hyperparameter Optimization with Dynamic Preference Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {437-446} }
Federated Continuous Category Discovery and Learning: Lixu Wang,

Chenxi Liu,

Junfeng Guo,

Qingqing Ye,

Heng Huang,

Haibo Hu,

Wei Dong; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Lixu and Liu, Chenxi and Guo, Junfeng and Ye, Qingqing and Huang, Heng and Hu, Haibo and Dong, Wei}, title = {Federated Continuous Category Discovery and Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2429-2439} }
Humans as a Calibration Pattern: Dynamic 3D Scene Reconstruction from Unsynchronized and Uncalibrated Videos: Changwoon Choi,

Jeongjun Kim,

Geonho Cha,

Minkwan Kim,

Dongyoon Wee,

Young Min Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Choi_2025_ICCV, author = {Choi, Changwoon and Kim, Jeongjun and Cha, Geonho and Kim, Minkwan and Wee, Dongyoon and Kim, Young Min}, title = {Humans as a Calibration Pattern: Dynamic 3D Scene Reconstruction from Unsynchronized and Uncalibrated Videos}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6598-6608} }
Decoupled Multi-Predictor Optimization for Inference-Efficient Model Tuning: Liwei Luo,

Shuaitengyuan Li,

Dongwei Ren,

Qilong Wang,

Pengfei Zhu,

Qinghua Hu; [pdf] [supp]
[bibtex]
@InProceedings{Luo_2025_ICCV, author = {Luo, Liwei and Li, Shuaitengyuan and Ren, Dongwei and Wang, Qilong and Zhu, Pengfei and Hu, Qinghua}, title = {Decoupled Multi-Predictor Optimization for Inference-Efficient Model Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3628-3638} }
MPBR: Multimodal Progressive Bidirectional Reasoning for Open-Set Fine-Grained Recognition: Junfu Tan,

Peiguang Jing,

Yu Zhu,

Yu Liu; [pdf]
[bibtex]
@InProceedings{Tan_2025_ICCV, author = {Tan, Junfu and Jing, Peiguang and Zhu, Yu and Liu, Yu}, title = {MPBR: Multimodal Progressive Bidirectional Reasoning for Open-Set Fine-Grained Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1282-1291} }
TerraMind: Large-Scale Generative Multimodality for Earth Observation: Johannes Jakubik,

Felix Yang,

Benedikt Blumenstiel,

Erik Scheurer,

Rocco Sedona,

Stefano Maurogiovanni,

Jente Bosmans,

Nikolaos Dionelis,

Valerio Marsocci,

Niklas Kopp,

Rahul Ramachandran,

Paolo Fraccaro,

Thomas Brunschwiler,

Gabriele Cavallaro,

Juan Bernabe-Moreno,

Nicolas Longépé; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jakubik_2025_ICCV, author = {Jakubik, Johannes and Yang, Felix and Blumenstiel, Benedikt and Scheurer, Erik and Sedona, Rocco and Maurogiovanni, Stefano and Bosmans, Jente and Dionelis, Nikolaos and Marsocci, Valerio and Kopp, Niklas and Ramachandran, Rahul and Fraccaro, Paolo and Brunschwiler, Thomas and Cavallaro, Gabriele and Bernabe-Moreno, Juan and Long\'ep\'e, Nicolas}, title = {TerraMind: Large-Scale Generative Multimodality for Earth Observation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7383-7394} }
An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval: Jaeseok Byun,

Seokhyeon Jeong,

Wonjae Kim,

Sanghyuk Chun,

Taesup Moon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Byun_2025_ICCV, author = {Byun, Jaeseok and Jeong, Seokhyeon and Kim, Wonjae and Chun, Sanghyuk and Moon, Taesup}, title = {An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3895-3904} }
Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation for Semi-Supervised Lifelong Person Re-Identification: Kunlun Xu,

Fan Zhuo,

Jiangmeng Li,

Xu Zou,

Jiahuan Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2025_ICCV, author = {Xu, Kunlun and Zhuo, Fan and Li, Jiangmeng and Zou, Xu and Zhou, Jiahuan}, title = {Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation for Semi-Supervised Lifelong Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3564-3574} }
What to Distill? Fast Knowledge Distillation with Adaptive Sampling: Byungchul Chae,

Seonyeong Heo; [pdf] [supp]
[bibtex]
@InProceedings{Chae_2025_ICCV, author = {Chae, Byungchul and Heo, Seonyeong}, title = {What to Distill? Fast Knowledge Distillation with Adaptive Sampling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2407-2416} }
Revisiting Pool-based Prompt Learning for Few-shot Class-incremental Learning: Yongwei Jiang,

Yixiong Zou,

Yuhua Li,

Ruixuan Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2025_ICCV, author = {Jiang, Yongwei and Zou, Yixiong and Li, Yuhua and Li, Ruixuan}, title = {Revisiting Pool-based Prompt Learning for Few-shot Class-incremental Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1303-1313} }
Dynamic Multi-Layer Null Space Projection for Vision-Language Continual Learning: Borui Kang,

Lei Wang,

Zhiping Wu,

Tao Feng,

Yawen Li,

Yang Gao,

Wenbin Li; [pdf] [supp]
[bibtex]
@InProceedings{Kang_2025_ICCV, author = {Kang, Borui and Wang, Lei and Wu, Zhiping and Feng, Tao and Li, Yawen and Gao, Yang and Li, Wenbin}, title = {Dynamic Multi-Layer Null Space Projection for Vision-Language Continual Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2077-2086} }
Balanced Sharpness-Aware Minimization for Imbalanced Regression: Yahao Liu,

Qin Wang,

Lixin Duan,

Wen Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2025_ICCV, author = {Liu, Yahao and Wang, Qin and Duan, Lixin and Li, Wen}, title = {Balanced Sharpness-Aware Minimization for Imbalanced Regression}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6242-6251} }
SuperEvent: Cross-Modal Learning of Event-based Keypoint Detection for SLAM: Yannick Burkhardt,

Simon Schaefer,

Stefan Leutenegger; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Burkhardt_2025_ICCV, author = {Burkhardt, Yannick and Schaefer, Simon and Leutenegger, Stefan}, title = {SuperEvent: Cross-Modal Learning of Event-based Keypoint Detection for SLAM}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8918-8928} }
PRVQL: Progressive Knowledge-guided Refinement for Robust Egocentric Visual Query Localization: Bing Fan,

Yunhe Feng,

Yapeng Tian,

James Chenhao Liang,

Yuewei Lin,

Yan Huang,

Heng Fan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fan_2025_ICCV, author = {Fan, Bing and Feng, Yunhe and Tian, Yapeng and Liang, James Chenhao and Lin, Yuewei and Huang, Yan and Fan, Heng}, title = {PRVQL: Progressive Knowledge-guided Refinement for Robust Egocentric Visual Query Localization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5156-5165} }
Bayesian-Inspired Space-Time Superpixels: Kent Gauen,

Stanley Chan; [pdf] [supp]
[bibtex]
@InProceedings{Gauen_2025_ICCV, author = {Gauen, Kent and Chan, Stanley}, title = {Bayesian-Inspired Space-Time Superpixels}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5382-5391} }
FEVER-OOD: Free Energy Vulnerability Elimination for Robust Out-of-Distribution Detection: Brian K.S. Isaac-Medina,

Mauricio Che,

Yona Falinie A. Gaus,

Samet Akcay,

Toby P. Breckon; [pdf] [supp]
[bibtex]
@InProceedings{Isaac-Medina_2025_ICCV, author = {Isaac-Medina, Brian K.S. and Che, Mauricio and Gaus, Yona Falinie A. and Akcay, Samet and Breckon, Toby P.}, title = {FEVER-OOD: Free Energy Vulnerability Elimination for Robust Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4529-4538} }
TRNAS: A Training-Free Robust Neural Architecture Search: Yeming Yang,

Qingling Zhu,

Jianping Luo,

Ka-Chun Wong,

Qiuzhen Lin,

Jianqiang Li; [pdf] [supp]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Yeming and Zhu, Qingling and Luo, Jianping and Wong, Ka-Chun and Lin, Qiuzhen and Li, Jianqiang}, title = {TRNAS: A Training-Free Robust Neural Architecture Search}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2336-2345} }
Hierarchical Divide-and-Conquer Grouping for Classification Adaptation of Pre-Trained Models: Ziqian Lu,

Yunlong Yu,

Qinyue Tong,

Jun Liu; [pdf] [supp]
[bibtex]
@InProceedings{Lu_2025_ICCV, author = {Lu, Ziqian and Yu, Yunlong and Tong, Qinyue and Liu, Jun}, title = {Hierarchical Divide-and-Conquer Grouping for Classification Adaptation of Pre-Trained Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3575-3584} }
Hypergraph Clustering Network with Partial Attribute Imputation: Qianqian Wang,

Bowen Zhao,

Zhengming Ding,

Wei Feng,

Quanxue Gao; [pdf]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Qianqian and Zhao, Bowen and Ding, Zhengming and Feng, Wei and Gao, Quanxue}, title = {Hypergraph Clustering Network with Partial Attribute Imputation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2697-2706} }
RoboTron-Drive: All-in-One Large Multimodal Model for Autonomous Driving: Zhijian Huang,

Chengjian Feng,

Feng Yan,

Baihui Xiao,

Zequn Jie,

Yujie Zhong,

Xiaodan Liang,

Lin Ma; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2025_ICCV, author = {Huang, Zhijian and Feng, Chengjian and Yan, Feng and Xiao, Baihui and Jie, Zequn and Zhong, Yujie and Liang, Xiaodan and Ma, Lin}, title = {RoboTron-Drive: All-in-One Large Multimodal Model for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8011-8021} }
Long-Tailed Classification with Multi-Granularity Semantics: Yuting Liu,

Liu Yang,

Yu Wang; [pdf]
[bibtex]
@InProceedings{Liu_2025_ICCV, author = {Liu, Yuting and Yang, Liu and Wang, Yu}, title = {Long-Tailed Classification with Multi-Granularity Semantics}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4285-4294} }
Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats: Chen Ziwen,

Hao Tan,

Kai Zhang,

Sai Bi,

Fujun Luan,

Yicong Hong,

Li Fuxin,

Zexiang Xu; [pdf] [supp]
[bibtex]
@InProceedings{Ziwen_2025_ICCV, author = {Ziwen, Chen and Tan, Hao and Zhang, Kai and Bi, Sai and Luan, Fujun and Hong, Yicong and Fuxin, Li and Xu, Zexiang}, title = {Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4349-4359} }
Unlearning the Noisy Correspondence Makes CLIP More Robust: Haochen Han,

Alex Jinpeng Wang,

Peijun Ye,

Fangming Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2025_ICCV, author = {Han, Haochen and Wang, Alex Jinpeng and Ye, Peijun and Liu, Fangming}, title = {Unlearning the Noisy Correspondence Makes CLIP More Robust}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4518-4528} }
ReTracker: Exploring Image Matching for Robust Online Any Point Tracking: Dongli Tan,

Xingyi He,

Sida Peng,

Yiqing Gong,

Xing Zhu,

Jiaming Sun,

Ruizhen Hu,

Yujun Shen,

Hujun Bao,

Xiaowei Zhou; [pdf] [supp]
[bibtex]
@InProceedings{Tan_2025_ICCV, author = {Tan, Dongli and He, Xingyi and Peng, Sida and Gong, Yiqing and Zhu, Xing and Sun, Jiaming and Hu, Ruizhen and Shen, Yujun and Bao, Hujun and Zhou, Xiaowei}, title = {ReTracker: Exploring Image Matching for Robust Online Any Point Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4306-4316} }
OpenSubstance: A High-quality Measured Dataset of Multi-View and -Lighting Images and Shapes: Fan Pei,

Jinchen Bai,

Xiang Feng,

Zoubin Bi,

Kun Zhou,

Hongzhi Wu; [pdf]
[bibtex]
@InProceedings{Pei_2025_ICCV, author = {Pei, Fan and Bai, Jinchen and Feng, Xiang and Bi, Zoubin and Zhou, Kun and Wu, Hongzhi}, title = {OpenSubstance: A High-quality Measured Dataset of Multi-View and -Lighting Images and Shapes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5221-5231} }
Overcoming Dual Drift for Continual Long-Tailed Visual Question Answering: Feifei Zhang,

Zhihao Wang,

Xi Zhang,

Changsheng Xu; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Feifei and Wang, Zhihao and Zhang, Xi and Xu, Changsheng}, title = {Overcoming Dual Drift for Continual Long-Tailed Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4413-4423} }
GARF: Learning Generalizable 3D Reassembly for Real-World Fractures: Sihang Li,

Zeyu Jiang,

Grace Chen,

Chenyang Xu,

Siqi Tan,

Xue Wang,

Irving Fang,

Kristof Zyskowski,

Shannon P. McPherron,

Radu Iovita,

Chen Feng,

Jing Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Sihang and Jiang, Zeyu and Chen, Grace and Xu, Chenyang and Tan, Siqi and Wang, Xue and Fang, Irving and Zyskowski, Kristof and McPherron, Shannon P. and Iovita, Radu and Feng, Chen and Zhang, Jing}, title = {GARF: Learning Generalizable 3D Reassembly for Real-World Fractures}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5711-5721} }
Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics: Taowen Wang,

Cheng Han,

James Liang,

Wenhao Yang,

Dongfang Liu,

Luna Xinyu Zhang,

Qifan Wang,

Jiebo Luo,

Ruixiang Tang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Taowen and Han, Cheng and Liang, James and Yang, Wenhao and Liu, Dongfang and Zhang, Luna Xinyu and Wang, Qifan and Luo, Jiebo and Tang, Ruixiang}, title = {Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6948-6958} }
Scaling Language-Free Visual Representation Learning: David Fan,

Shengbang Tong,

Jiachen Zhu,

Koustuv Sinha,

Zhuang Liu,

Xinlei Chen,

Michael Rabbat,

Nicolas Ballas,

Yann LeCun,

Amir Bar,

Saining Xie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fan_2025_ICCV, author = {Fan, David and Tong, Shengbang and Zhu, Jiachen and Sinha, Koustuv and Liu, Zhuang and Chen, Xinlei and Rabbat, Michael and Ballas, Nicolas and LeCun, Yann and Bar, Amir and Xie, Saining}, title = {Scaling Language-Free Visual Representation Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {370-382} }
Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation: Ziyu Zhu,

Xilin Wang,

Yixuan Li,

Zhuofan Zhang,

Xiaojian Ma,

Yixin Chen,

Baoxiong Jia,

Wei Liang,

Qian Yu,

Zhidong Deng,

Siyuan Huang,

Qing Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2025_ICCV, author = {Zhu, Ziyu and Wang, Xilin and Li, Yixuan and Zhang, Zhuofan and Ma, Xiaojian and Chen, Yixin and Jia, Baoxiong and Liang, Wei and Yu, Qian and Deng, Zhidong and Huang, Siyuan and Li, Qing}, title = {Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8120-8132} }
Exploring The Visual Feature Space for Multimodal Neural Decoding: Weihao Xia,

Cengiz Oztireli; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xia_2025_ICCV, author = {Xia, Weihao and Oztireli, Cengiz}, title = {Exploring The Visual Feature Space for Multimodal Neural Decoding}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4370-4379} }
INS-MMBench: A Comprehensive Benchmark for Evaluating LVLMs' Performance in Insurance: Chenwei Lin,

Hanjia Lyu,

Xian Xu,

Jiebo Luo; [pdf] [supp]
[bibtex]
@InProceedings{Lin_2025_ICCV, author = {Lin, Chenwei and Lyu, Hanjia and Xu, Xian and Luo, Jiebo}, title = {INS-MMBench: A Comprehensive Benchmark for Evaluating LVLMs' Performance in Insurance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9036-9047} }
Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLMs: Xinyu Fang,

Zhijian Chen,

Kai Lan,

Lixin Ma,

Shengyuan Ding,

Yingji Liang,

Xiangyu Zhao,

Farong Wen,

Zicheng Zhang,

Guofeng Zhang,

Haodong Duan,

Kai Chen,

Dahua Lin; [pdf] [supp]
[bibtex]
@InProceedings{Fang_2025_ICCV, author = {Fang, Xinyu and Chen, Zhijian and Lan, Kai and Ma, Lixin and Ding, Shengyuan and Liang, Yingji and Zhao, Xiangyu and Wen, Farong and Zhang, Zicheng and Zhang, Guofeng and Duan, Haodong and Chen, Kai and Lin, Dahua}, title = {Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLMs}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {447-456} }
Boosting Adversarial Transferability via Residual Perturbation Attack: Jinjia Peng,

Zeze Tao,

Huibing Wang,

Meng Wang,

Yang Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Peng_2025_ICCV, author = {Peng, Jinjia and Tao, Zeze and Wang, Huibing and Wang, Meng and Wang, Yang}, title = {Boosting Adversarial Transferability via Residual Perturbation Attack}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1261-1270} }
LDPose: Towards Inclusive Human Pose Estimation for Limb-Deficient Individuals in the Wild: Jiaying Ying,

Heming Du,

Kaihao Zhang,

Lincheng Li,

Xin Yu; [pdf] [supp]
[bibtex]
@InProceedings{Ying_2025_ICCV, author = {Ying, Jiaying and Du, Heming and Zhang, Kaihao and Li, Lincheng and Yu, Xin}, title = {LDPose: Towards Inclusive Human Pose Estimation for Limb-Deficient Individuals in the Wild}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9865-9875} }
Language-Driven Multi-Label Zero-Shot Learning with Semantic Granularity: Shouwen Wang,

Qian Wan,

Junbin Gao,

Zhigang Zeng; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Shouwen and Wan, Qian and Gao, Junbin and Zeng, Zhigang}, title = {Language-Driven Multi-Label Zero-Shot Learning with Semantic Granularity}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1968-1978} }
Differentiable Room Acoustic Rendering with Multi-View Vision Priors: Derong Jin,

Ruohan Gao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jin_2025_ICCV, author = {Jin, Derong and Gao, Ruohan}, title = {Differentiable Room Acoustic Rendering with Multi-View Vision Priors}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {37-47} }
AgroBench: Vision-Language Model Benchmark in Agriculture: Risa Shinoda,

Nakamasa Inoue,

Hirokatsu Kataoka,

Masaki Onishi,

Yoshitaka Ushiku; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shinoda_2025_ICCV, author = {Shinoda, Risa and Inoue, Nakamasa and Kataoka, Hirokatsu and Onishi, Masaki and Ushiku, Yoshitaka}, title = {AgroBench: Vision-Language Model Benchmark in Agriculture}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7634-7644} }
Adding Additional Control to One-Step Diffusion with Joint Distribution Matching: Yihong Luo,

Tianyang Hu,

Yifan Song,

Jiacheng Sun,

Zhenguo Li,

Jing Tang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Luo_2025_ICCV, author = {Luo, Yihong and Hu, Tianyang and Song, Yifan and Sun, Jiacheng and Li, Zhenguo and Tang, Jing}, title = {Adding Additional Control to One-Step Diffusion with Joint Distribution Matching}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4009-4018} }
Flexi-FSCIL: Adaptive Knowledge Retention for Breaking the Stability-Plasticity Dilemma in Few-Shot Class-Incremental Learning: Wufei Xie,

Yalin Wang,

Chenliang Liu,

Zhaohui Jiang,

Xue Yang; [pdf]
[bibtex]
@InProceedings{Xie_2025_ICCV, author = {Xie, Wufei and Wang, Yalin and Liu, Chenliang and Jiang, Zhaohui and Yang, Xue}, title = {Flexi-FSCIL: Adaptive Knowledge Retention for Breaking the Stability-Plasticity Dilemma in Few-Shot Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2451-2460} }
How To Make Your Cell Tracker Say "I dunno!": Richard D. Paul,

Johannes Seiffarth,

David Rügamer,

Katharina Nöh,

Hanno Scharr; [pdf] [supp]
[bibtex]
@InProceedings{Paul_2025_ICCV, author = {Paul, Richard D. and Seiffarth, Johannes and R\"ugamer, David and N\"oh, Katharina and Scharr, Hanno}, title = {How To Make Your Cell Tracker Say ''I dunno!''}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6914-6923} }
SDFit: 3D Object Pose and Shape by Fitting a Morphable SDF to a Single Image: Dimitrije Antić,

Georgios Paschalidis,

Shashank Tripathi,

Theo Gevers,

Sai Kumar Dwivedi,

Dimitrios Tzionas; [pdf] [supp]
[bibtex]
@InProceedings{Antic_2025_ICCV, author = {Anti\'c, Dimitrije and Paschalidis, Georgios and Tripathi, Shashank and Gevers, Theo and Dwivedi, Sai Kumar and Tzionas, Dimitrios}, title = {SDFit: 3D Object Pose and Shape by Fitting a Morphable SDF to a Single Image}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9616-9626} }
VRM: Knowledge Distillation via Virtual Relation Matching: Weijia Zhang,

Fei Xie,

Weidong Cai,

Chao Ma; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Weijia and Xie, Fei and Cai, Weidong and Ma, Chao}, title = {VRM: Knowledge Distillation via Virtual Relation Matching}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2707-2717} }
ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models: Hyun Jun Yook,

Ga San Jhun,

Jae Hyun Cho,

Min Jeon,

Donghyun Kim,

Tae Hyung Kim,

Youn Kyu Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yook_2025_ICCV, author = {Yook, Hyun Jun and Jhun, Ga San and Cho, Jae Hyun and Jeon, Min and Kim, Donghyun and Kim, Tae Hyung and Lee, Youn Kyu}, title = {ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3926-3935} }
GECO: Geometrically Consistent Embedding with Lightspeed Inference: Regine Hartwig,

Dominik Muhle,

Riccardo Marin,

Daniel Cremers; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hartwig_2025_ICCV, author = {Hartwig, Regine and Muhle, Dominik and Marin, Riccardo and Cremers, Daniel}, title = {GECO: Geometrically Consistent Embedding with Lightspeed Inference}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9309-9319} }
Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion: Massimiliano Viola,

Kevin Qu,

Nando Metzger,

Bingxin Ke,

Alexander Becker,

Konrad Schindler,

Anton Obukhov; [pdf]
[bibtex]
@InProceedings{Viola_2025_ICCV, author = {Viola, Massimiliano and Qu, Kevin and Metzger, Nando and Ke, Bingxin and Becker, Alexander and Schindler, Konrad and Obukhov, Anton}, title = {Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5359-5370} }
TurboTrain: Towards Efficient and Balanced Multi-Task Learning for Multi-Agent Perception and Prediction: Zewei Zhou,

Seth Z. Zhao,

Tianhui Cai,

Zhiyu Huang,

Bolei Zhou,

Jiaqi Ma; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2025_ICCV, author = {Zhou, Zewei and Zhao, Seth Z. and Cai, Tianhui and Huang, Zhiyu and Zhou, Bolei and Ma, Jiaqi}, title = {TurboTrain: Towards Efficient and Balanced Multi-Task Learning for Multi-Agent Perception and Prediction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4391-4402} }
Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentation: Yihong Cao,

Jiaming Zhang,

Xu Zheng,

Hao Shi,

Kunyu Peng,

Hang Liu,

Kailun Yang,

Hui Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2025_ICCV, author = {Cao, Yihong and Zhang, Jiaming and Zheng, Xu and Shi, Hao and Peng, Kunyu and Liu, Hang and Yang, Kailun and Zhang, Hui}, title = {Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8961-8972} }
Boosting Adversarial Transferability via Negative Hessian Trace Regularization: Yunfei Long,

Zilin Tian,

Liguo Zhang,

Huosheng Xu; [pdf] [supp]
[bibtex]
@InProceedings{Long_2025_ICCV, author = {Long, Yunfei and Tian, Zilin and Zhang, Liguo and Xu, Huosheng}, title = {Boosting Adversarial Transferability via Negative Hessian Trace Regularization}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2386-2395} }
AutoOcc: Automatic Open-Ended Semantic Occupancy Annotation via Vision-Language Guided Gaussian Splatting: Xiaoyu Zhou,

Jingqi Wang,

Yongtao Wang,

Yufei Wei,

Nan Dong,

Ming-Hsuan Yang; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhou_2025_ICCV, author = {Zhou, Xiaoyu and Wang, Jingqi and Wang, Yongtao and Wei, Yufei and Dong, Nan and Yang, Ming-Hsuan}, title = {AutoOcc: Automatic Open-Ended Semantic Occupancy Annotation via Vision-Language Guided Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3367-3377} }
Improving Noise Efficiency in Privacy-preserving Dataset Distillation: Runkai Zheng,

Vishnu Asutosh Dasu,

Yinong Oliver Wang,

Haohan Wang,

Fernando De La Torre; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2025_ICCV, author = {Zheng, Runkai and Dasu, Vishnu Asutosh and Wang, Yinong Oliver and Wang, Haohan and De La Torre, Fernando}, title = {Improving Noise Efficiency in Privacy-preserving Dataset Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4838-4847} }
Parameter-Efficient Adaptation of Geospatial Foundation Models through Embedding Deflection: Romain Thoreau,

Valerio Marsocci,

Dawa Derksen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Thoreau_2025_ICCV, author = {Thoreau, Romain and Marsocci, Valerio and Derksen, Dawa}, title = {Parameter-Efficient Adaptation of Geospatial Foundation Models through Embedding Deflection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9594-9604} }
Coupling the Generator with Teacher for Effective Data-Free Knowledge Distillation: Xu Chen,

Yang Li,

Yahong Han,

Guangquan Xu,

Jialie Shen; [pdf]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Xu and Li, Yang and Han, Yahong and Xu, Guangquan and Shen, Jialie}, title = {Coupling the Generator with Teacher for Effective Data-Free Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2152-2160} }
Harnessing Input-Adaptive Inference for Efficient VLN: Dongwoo Kang,

Akhil Perincherry,

Zachary Coalson,

Aiden Gabriel,

Stefan Lee,

Sanghyun Hong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kang_2025_ICCV, author = {Kang, Dongwoo and Perincherry, Akhil and Coalson, Zachary and Gabriel, Aiden and Lee, Stefan and Hong, Sanghyun}, title = {Harnessing Input-Adaptive Inference for Efficient VLN}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8219-8229} }
EMatch: A Unified Framework for Event-based Optical Flow and Stereo Matching: Pengjie Zhang,

Lin Zhu,

Xiao Wang,

Lizhi Wang,

Hua Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Pengjie and Zhu, Lin and Wang, Xiao and Wang, Lizhi and Huang, Hua}, title = {EMatch: A Unified Framework for Event-based Optical Flow and Stereo Matching}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5845-5855} }
ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models: Zifu Wan,

Ce Zhang,

Silong Yong,

Martin Q. Ma,

Simon Stepputtis,

Louis-Philippe Morency,

Deva Ramanan,

Katia Sycara,

Yaqi Xie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wan_2025_ICCV, author = {Wan, Zifu and Zhang, Ce and Yong, Silong and Ma, Martin Q. and Stepputtis, Simon and Morency, Louis-Philippe and Ramanan, Deva and Sycara, Katia and Xie, Yaqi}, title = {ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3225-3234} }
Kestrel: 3D Multimodal LLM for Part-Aware Grounded Description: Mahmoud Ahmed,

Junjie Fei,

Jian Ding,

Eslam Mohamed Bakr,

Mohamed Elhoseiny; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ahmed_2025_ICCV, author = {Ahmed, Mahmoud and Fei, Junjie and Ding, Jian and Bakr, Eslam Mohamed and Elhoseiny, Mohamed}, title = {Kestrel: 3D Multimodal LLM for Part-Aware Grounded Description}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8973-8983} }
EquiCaps: Predictor-Free Pose-Aware Pre-Trained Capsule Networks: Athinoulla Konstantinou,

Georgios Leontidis,

Mamatha Thota,

Aiden Durrant; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Konstantinou_2025_ICCV, author = {Konstantinou, Athinoulla and Leontidis, Georgios and Thota, Mamatha and Durrant, Aiden}, title = {EquiCaps: Predictor-Free Pose-Aware Pre-Trained Capsule Networks}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7947-7957} }
Feature Decomposition-Recomposition in Large Vision-Language Model for Few-Shot Class-Incremental Learning: Zongyao Xue,

Meina Kan,

Shiguang Shan,

Xilin Chen; [pdf] [supp]
[bibtex]
@InProceedings{Xue_2025_ICCV, author = {Xue, Zongyao and Kan, Meina and Shan, Shiguang and Chen, Xilin}, title = {Feature Decomposition-Recomposition in Large Vision-Language Model for Few-Shot Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3153-3162} }
Taming Flow Matching with Unbalanced Optimal Transport into Fast Pansharpening: Zihan Cao,

Yu Zhong,

Liang-Jian Deng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2025_ICCV, author = {Cao, Zihan and Zhong, Yu and Deng, Liang-Jian}, title = {Taming Flow Matching with Unbalanced Optimal Transport into Fast Pansharpening}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2803-2813} }
Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning: Gaurav Patel,

Qiang Qiu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Patel_2025_ICCV, author = {Patel, Gaurav and Qiu, Qiang}, title = {Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4211-4221} }
Scaling and Taming Adversarial Training with Synthetic Data: Juntao Wu,

Xianting Huang,

Yu Chen,

Shuai Pang,

Ke Wang; [pdf]
[bibtex]
@InProceedings{Wu_2025_ICCV, author = {Wu, Juntao and Huang, Xianting and Chen, Yu and Pang, Shuai and Wang, Ke}, title = {Scaling and Taming Adversarial Training with Synthetic Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2951-2960} }
Removing Cost Volumes from Optical Flow Estimators: Simon Kiefhaber,

Stefan Roth,

Simone Schaub-Meyer; [pdf] [supp]
[bibtex]
@InProceedings{Kiefhaber_2025_ICCV, author = {Kiefhaber, Simon and Roth, Stefan and Schaub-Meyer, Simone}, title = {Removing Cost Volumes from Optical Flow Estimators}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {79-89} }
Cross-modal Ship Re-Identification via Optical and SAR Imagery: A Novel Dataset and Method: Han Wang,

Shengyang Li,

Jian Yang,

Yuxuan Liu,

Yixuan Lv,

Zhuang Zhou; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Han and Li, Shengyang and Yang, Jian and Liu, Yuxuan and Lv, Yixuan and Zhou, Zhuang}, title = {Cross-modal Ship Re-Identification via Optical and SAR Imagery: A Novel Dataset and Method}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7873-7883} }
Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation: Wenyao Zhang,

Hongsi Liu,

Bohan Li,

Jiawei He,

Zekun Qi,

Yunnan Wang,

Shengyang Zhao,

Xinqiang Yu,

Wenjun Zeng,

Xin Jin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Wenyao and Liu, Hongsi and Li, Bohan and He, Jiawei and Qi, Zekun and Wang, Yunnan and Zhao, Shengyang and Yu, Xinqiang and Zeng, Wenjun and Jin, Xin}, title = {Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6678-6692} }
MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion: Zihan Wang,

Jeff Tan,

Tarasha Khurana,

Neehar Peri,

Deva Ramanan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2025_ICCV, author = {Wang, Zihan and Tan, Jeff and Khurana, Tarasha and Peri, Neehar and Ramanan, Deva}, title = {MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8252-8263} }
SIGMAN: Scaling 3D Human Gaussian Generation with Millions of Assets: Yuhang Yang,

Fengqi Liu,

Yixing Lu,

Qin Zhao,

Pingyu Wu,

Wei Zhai,

Ran Yi,

Yang Cao,

Lizhuang Ma,

Zheng-Jun Zha,

Junting Dong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Yuhang and Liu, Fengqi and Lu, Yixing and Zhao, Qin and Wu, Pingyu and Zhai, Wei and Yi, Ran and Cao, Yang and Ma, Lizhuang and Zha, Zheng-Jun and Dong, Junting}, title = {SIGMAN: Scaling 3D Human Gaussian Generation with Millions of Assets}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5122-5133} }
Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy: Zhi Hou,

Tianyi Zhang,

Yuwen Xiong,

Haonan Duan,

Hengjun Pu,

Ronglei Tong,

Chengyang Zhao,

Xizhou Zhu,

Yu Qiao,

Jifeng Dai,

Yuntao Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hou_2025_ICCV, author = {Hou, Zhi and Zhang, Tianyi and Xiong, Yuwen and Duan, Haonan and Pu, Hengjun and Tong, Ronglei and Zhao, Chengyang and Zhu, Xizhou and Qiao, Yu and Dai, Jifeng and Chen, Yuntao}, title = {Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7686-7697} }
GLEAM: Enhanced Transferable Adversarial Attacks for Vision-Language Pre-training Models via Global-Local Transformations: Yunqi Liu,

Xue Ouyang,

Xiaohui Cui; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2025_ICCV, author = {Liu, Yunqi and Ouyang, Xue and Cui, Xiaohui}, title = {GLEAM: Enhanced Transferable Adversarial Attacks for Vision-Language Pre-training Models via Global-Local Transformations}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1665-1674} }
CaliMatch: Adaptive Calibration for Improving Safe Semi-supervised Learning: Jinsoo Bae,

Seoung Bum Kim,

Hyungrok Do; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bae_2025_ICCV, author = {Bae, Jinsoo and Kim, Seoung Bum and Do, Hyungrok}, title = {CaliMatch: Adaptive Calibration for Improving Safe Semi-supervised Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2867-2876} }
Aligning Vision to Language: Annotation-Free Multimodal Knowledge Graph Construction for Enhanced LLMs Reasoning: Junming Liu,

Siyuan Meng,

Yanting Gao,

Song Mao,

Pinlong Cai,

Guohang Yan,

Yirong Chen,

Zilin Bian,

Ding Wang,

Botian Shi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2025_ICCV, author = {Liu, Junming and Meng, Siyuan and Gao, Yanting and Mao, Song and Cai, Pinlong and Yan, Guohang and Chen, Yirong and Bian, Zilin and Wang, Ding and Shi, Botian}, title = {Aligning Vision to Language: Annotation-Free Multimodal Knowledge Graph Construction for Enhanced LLMs Reasoning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {981-992} }
GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability: Zhenghao He,

Sanchit Sinha,

Guangzhi Xiong,

Aidong Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{He_2025_ICCV, author = {He, Zhenghao and Sinha, Sanchit and Xiong, Guangzhi and Zhang, Aidong}, title = {GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {614-623} }
PhysRig: Differentiable Physics-Based Skinning and Rigging Framework for Realistic Articulated Object Modeling: Hao Zhang,

Haolan Xu,

Chun Feng,

Varun Jampani,

Narendra Ahuja; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2025_ICCV, author = {Zhang, Hao and Xu, Haolan and Feng, Chun and Jampani, Varun and Ahuja, Narendra}, title = {PhysRig: Differentiable Physics-Based Skinning and Rigging Framework for Realistic Articulated Object Modeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6609-6620} }
Open-set Cross Modal Generalization via Multimodal Unified Representation: Hai Huang,

Yan Xia,

Shulei Wang,

Hanting Wang,

Minghui Fang,

Shengpeng Ji,

Sashuai Zhou,

Tao Jin,

Zhou Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2025_ICCV, author = {Huang, Hai and Xia, Yan and Wang, Shulei and Wang, Hanting and Fang, Minghui and Ji, Shengpeng and Zhou, Sashuai and Jin, Tao and Zhao, Zhou}, title = {Open-set Cross Modal Generalization via Multimodal Unified Representation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {541-551} }
GT-Loc: Unifying When and Where in Images Through a Joint Embedding Space: David G. Shatwell,

Ishan Rajendrakumar Dave,

Sirnam Swetha,

Mubarak Shah; [pdf] [supp]
[bibtex]
@InProceedings{Shatwell_2025_ICCV, author = {Shatwell, David G. and Dave, Ishan Rajendrakumar and Swetha, Sirnam and Shah, Mubarak}, title = {GT-Loc: Unifying When and Where in Images Through a Joint Embedding Space}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1-11} }
MATE: Motion-Augmented Temporal Consistency for Event-based Point Tracking: Han Han,

Wei Zhai,

Yang Cao,

Bin Li,

Zheng-jun Zha; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2025_ICCV, author = {Han, Han and Zhai, Wei and Cao, Yang and Li, Bin and Zha, Zheng-jun}, title = {MATE: Motion-Augmented Temporal Consistency for Event-based Point Tracking}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8340-8349} }
Diffusion-Based Extreme High-speed Scenes Reconstruction with the Complementary Vision Sensor: Yapeng Meng,

Yihan Lin,

Taoyi Wang,

Yuguo Chen,

Lijian Wang,

Rong Zhao; [pdf] [supp]
[bibtex]
@InProceedings{Meng_2025_ICCV, author = {Meng, Yapeng and Lin, Yihan and Wang, Taoyi and Chen, Yuguo and Wang, Lijian and Zhao, Rong}, title = {Diffusion-Based Extreme High-speed Scenes Reconstruction with the Complementary Vision Sensor}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5701-5710} }
RnGCam: High-speed video from rolling & global shutter measurements: Kevin Tandi,

Xiang Dai,

Chinmay Talegaonkar,

Gal Mishne,

Nick Antipa; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tandi_2025_ICCV, author = {Tandi, Kevin and Dai, Xiang and Talegaonkar, Chinmay and Mishne, Gal and Antipa, Nick}, title = {RnGCam: High-speed video from rolling \& global shutter measurements}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8830-8840} }
OV3D-CG: Open-vocabulary 3D Instance Segmentation with Contextual Guidance: Mingquan Zhou,

Chen He,

Ruiping Wang,

Xilin Chen; [pdf] [supp]
[bibtex]
@InProceedings{Zhou_2025_ICCV, author = {Zhou, Mingquan and He, Chen and Wang, Ruiping and Chen, Xilin}, title = {OV3D-CG: Open-vocabulary 3D Instance Segmentation with Contextual Guidance}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5305-5314} }
FG-OrIU: Towards Better Forgetting via Feature-Gradient Orthogonality for Incremental Unlearning: Qian Feng,

JiaHang Tu,

Mintong Kang,

Hanbin Zhao,

Chao Zhang,

Hui Qian; [pdf] [supp]
[bibtex]
@InProceedings{Feng_2025_ICCV, author = {Feng, Qian and Tu, JiaHang and Kang, Mintong and Zhao, Hanbin and Zhang, Chao and Qian, Hui}, title = {FG-OrIU: Towards Better Forgetting via Feature-Gradient Orthogonality for Incremental Unlearning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {1957-1967} }
After the Party: Navigating the Mapping From Color to Ambient Lighting: Florin-Alexandru Vasluianu,

Tim Seizinger,

Zongwei Wu,

Radu Timofte; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Vasluianu_2025_ICCV, author = {Vasluianu, Florin-Alexandru and Seizinger, Tim and Wu, Zongwei and Timofte, Radu}, title = {After the Party: Navigating the Mapping From Color to Ambient Lighting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9218-9229} }
DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimation: Yue-Jiang Dong,

Wang Zhao,

Jiale Xu,

Ying Shan,

Song-Hai Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Dong_2025_ICCV, author = {Dong, Yue-Jiang and Zhao, Wang and Xu, Jiale and Shan, Ying and Zhang, Song-Hai}, title = {DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5415-5425} }
InfoBridge: Balanced Multimodal Integration through Conditional Dependency Modeling: Chenxin Li,

Yifan Liu,

Panwang Pan,

Hengyu Liu,

Xinyu Liu,

Wuyang Li,

Cheng Wang,

Weihao Yu,

Yiyang Lin,

Yixuan Yuan; [pdf]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Chenxin and Liu, Yifan and Pan, Panwang and Liu, Hengyu and Liu, Xinyu and Li, Wuyang and Wang, Cheng and Yu, Weihao and Lin, Yiyang and Yuan, Yixuan}, title = {InfoBridge: Balanced Multimodal Integration through Conditional Dependency Modeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {393-404} }
One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models: Jiale Zhao,

Xinyang Jiang,

Junyao Gao,

Yuhao Xue,

Cairong Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2025_ICCV, author = {Zhao, Jiale and Jiang, Xinyang and Gao, Junyao and Xue, Yuhao and Zhao, Cairong}, title = {One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {187-196} }
CHROME: Clothed Human Reconstruction with Occlusion-Resilience and Multiview-Consistency from a Single Image: Arindam Dutta,

Meng Zheng,

Zhongpai Gao,

Benjamin Planche,

Anwesa Choudhuri,

Terrence Chen,

Amit K. Roy-Chowdhury,

Ziyan Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dutta_2025_ICCV, author = {Dutta, Arindam and Zheng, Meng and Gao, Zhongpai and Planche, Benjamin and Choudhuri, Anwesa and Chen, Terrence and Roy-Chowdhury, Amit K. and Wu, Ziyan}, title = {CHROME: Clothed Human Reconstruction with Occlusion-Resilience and Multiview-Consistency from a Single Image}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9124-9135} }
H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction: Heng Jia,

Linchao Zhu,

Na Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jia_2025_ICCV, author = {Jia, Heng and Zhu, Linchao and Zhao, Na}, title = {H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7655-7665} }
3D Gaussian Map with Open-Set Semantic Grouping for Vision-Language Navigation: Jianzhe Gao,

Rui Liu,

Wenguan Wang; [pdf] [supp]
[bibtex]
@InProceedings{Gao_2025_ICCV, author = {Gao, Jianzhe and Liu, Rui and Wang, Wenguan}, title = {3D Gaussian Map with Open-Set Semantic Grouping for Vision-Language Navigation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {9252-9262} }
M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision: Kailai Zhou,

Fuqiang Yang,

Shixian Wang,

Bihan Wen,

Chongde Zi,

Linsen Chen,

Qiu Shen,

Xun Cao; [pdf] [supp]
[bibtex]
@InProceedings{Zhou_2025_ICCV, author = {Zhou, Kailai and Yang, Fuqiang and Wang, Shixian and Wen, Bihan and Zi, Chongde and Chen, Linsen and Shen, Qiu and Cao, Xun}, title = {M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7861-7872} }
Joint Learning of Pose Regression and Denoising Diffusion with Score Scaling Sampling for Category-level 6D Pose Estimation: Seunghyun Lee,

Tae-Kyun Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2025_ICCV, author = {Lee, Seunghyun and Kim, Tae-Kyun}, title = {Joint Learning of Pose Regression and Denoising Diffusion with Score Scaling Sampling for Category-level 6D Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {5757-5768} }
Continual Adaptation: Environment-Conditional Parameter Generation for Object Detection in Dynamic Scenarios: Deng Li,

Aming Wu,

Yang Li,

Yaowei Wang,

Yahong Han; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Deng and Wu, Aming and Li, Yang and Wang, Yaowei and Han, Yahong}, title = {Continual Adaptation: Environment-Conditional Parameter Generation for Object Detection in Dynamic Scenarios}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4434-4443} }
CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning: Duo Wu,

Jinghe Wang,

Yuan Meng,

Yanning Zhang,

Le Sun,

Zhi Wang; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2025_ICCV, author = {Wu, Duo and Wang, Jinghe and Meng, Yuan and Zhang, Yanning and Sun, Le and Wang, Zhi}, title = {CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8699-8709} }
Progressive Distribution Bridging: Unsupervised Adaptation for Large-scale Pre-trained Models via Adaptive Auxiliary Data: Weinan He,

Yixin Zhang,

Zilei Wang; [pdf] [supp]
[bibtex]
@InProceedings{He_2025_ICCV, author = {He, Weinan and Zhang, Yixin and Wang, Zilei}, title = {Progressive Distribution Bridging: Unsupervised Adaptation for Large-scale Pre-trained Models via Adaptive Auxiliary Data}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3280-3292} }
VPR-Cloak: A First Look at Privacy Cloak Against Visual Place Recognition: Shuting Dong,

Mingzhi Chen,

Feng Lu,

Hao Yu,

Guanghao Li,

Zhe Wu,

Ming Tang,

Chun Yuan; [pdf] [supp]
[bibtex]
@InProceedings{Dong_2025_ICCV, author = {Dong, Shuting and Chen, Mingzhi and Lu, Feng and Yu, Hao and Li, Guanghao and Wu, Zhe and Tang, Ming and Yuan, Chun}, title = {VPR-Cloak: A First Look at Privacy Cloak Against Visual Place Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {7197-7208} }
Improving Multimodal Learning via Imbalanced Learning: Shicai Wei,

Chunbo Luo,

Yang Luo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wei_2025_ICCV, author = {Wei, Shicai and Luo, Chunbo and Luo, Yang}, title = {Improving Multimodal Learning via Imbalanced Learning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2250-2259} }
INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling: Xin Dong,

Shichao Dong,

Jin Wang,

Jing Huang,

Li Zhou,

Zenghui Sun,

Lihua Jing,

Jinsong Lan,

Xiaoyong Zhu,

Bo Zheng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dong_2025_ICCV, author = {Dong, Xin and Dong, Shichao and Wang, Jin and Huang, Jing and Zhou, Li and Sun, Zenghui and Jing, Lihua and Lan, Jinsong and Zhu, Xiaoyong and Zheng, Bo}, title = {INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2534-2544} }
Medical World Model: Yijun Yang,

Zhao-Yang Wang,

Qiuping Liu,

Shuwen Sun,

Kang Wang,

Rama Chellappa,

Zongwei Zhou,

Alan Yuille,

Lei Zhu,

Yu-Dong Zhang,

Jieneng Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2025_ICCV, author = {Yang, Yijun and Wang, Zhao-Yang and Liu, Qiuping and Sun, Shuwen and Wang, Kang and Chellappa, Rama and Zhou, Zongwei and Yuille, Alan and Zhu, Lei and Zhang, Yu-Dong and Chen, Jieneng}, title = {Medical World Model}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8319-8329} }
RoMo: Robust Motion Segmentation Improves Structure from Motion: Lily Goli,

Sara Sabour,

Mark Matthews,

Marcus A. Brubaker,

Dmitry Lagun,

Alec Jacobson,

David J. Fleet,

Saurabh Saxena,

Andrea Tagliasacchi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Goli_2025_ICCV, author = {Goli, Lily and Sabour, Sara and Matthews, Mark and Brubaker, Marcus A. and Lagun, Dmitry and Jacobson, Alec and Fleet, David J. and Saxena, Saurabh and Tagliasacchi, Andrea}, title = {RoMo: Robust Motion Segmentation Improves Structure from Motion}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6155-6164} }
Robust Low-light Scene Restoration via Illumination Transition: Ze Li,

Feng Zhang,

Xiatian Zhu,

Meng Zhang,

Yanghong Zhou,

P. Y. Mok; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Ze and Zhang, Feng and Zhu, Xiatian and Zhang, Meng and Zhou, Yanghong and Mok, P. Y.}, title = {Robust Low-light Scene Restoration via Illumination Transition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6188-6197} }
Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning: Weitai Kang,

Haifeng Huang,

Yuzhang Shang,

Mubarak Shah,

Yan Yan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kang_2025_ICCV, author = {Kang, Weitai and Huang, Haifeng and Shang, Yuzhang and Shah, Mubarak and Yan, Yan}, title = {Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {3905-3915} }
ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for MLLM-based Process Judges: Jiaxin Ai,

Pengfei Zhou,

Zhaopan Xu,

Ming Li,

Fanrui Zhang,

Zizhen Li,

Jianwen Sun,

Yukang Feng,

Baojin Huang,

Zhongyuan Wang,

Kaipeng Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ai_2025_ICCV, author = {Ai, Jiaxin and Zhou, Pengfei and Xu, Zhaopan and Li, Ming and Zhang, Fanrui and Li, Zizhen and Sun, Jianwen and Feng, Yukang and Huang, Baojin and Wang, Zhongyuan and Zhang, Kaipeng}, title = {ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for MLLM-based Process Judges}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4681-4690} }
GloPER: Unsupervised Animal Pattern Extraction from Local Reconstruction: Bowen Chen,

Yun Sing Koh,

Gillian Dobbie; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2025_ICCV, author = {Chen, Bowen and Koh, Yun Sing and Dobbie, Gillian}, title = {GloPER: Unsupervised Animal Pattern Extraction from Local Reconstruction}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6519-6529} }
COSTARR: Consolidated Open Set Technique with Attenuation for Robust Recognition: Ryan Rabinowitz,

Steve Cruz,

Walter Scheirer,

Terrance E. Boult; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rabinowitz_2025_ICCV, author = {Rabinowitz, Ryan and Cruz, Steve and Scheirer, Walter and Boult, Terrance E.}, title = {COSTARR: Consolidated Open Set Technique with Attenuation for Robust Recognition}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4146-4155} }
CCMNet: Leveraging Calibrated Color Correction Matrices for Cross-Camera Color Constancy: Dongyoung Kim,

Mahmoud Afifi,

Dongyun Kim,

Michael S. Brown,

Seon Joo Kim; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2025_ICCV, author = {Kim, Dongyoung and Afifi, Mahmoud and Kim, Dongyun and Brown, Michael S. and Kim, Seon Joo}, title = {CCMNet: Leveraging Calibrated Color Correction Matrices for Cross-Camera Color Constancy}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6198-6208} }
Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification: Tuo Xiang,

Xuemiao Xu,

Bangzhen Liu,

Jinyi Li,

Yong Li,

Shengfeng He; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiang_2025_ICCV, author = {Xiang, Tuo and Xu, Xuemiao and Liu, Bangzhen and Li, Jinyi and Li, Yong and He, Shengfeng}, title = {Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {6761-6771} }
Secure On-Device Video OOD Detection Without Backpropagation: Shawn Li,

Peilin Cai,

Yuxiao Zhou,

Zhiyu Ni,

Renjie Liang,

You Qin,

Yi Nian,

Zhengzhong Tu,

Xiyang Hu,

Yue Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2025_ICCV, author = {Li, Shawn and Cai, Peilin and Zhou, Yuxiao and Ni, Zhiyu and Liang, Renjie and Qin, You and Nian, Yi and Tu, Zhengzhong and Hu, Xiyang and Zhao, Yue}, title = {Secure On-Device Video OOD Detection Without Backpropagation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {112-121} }
Underwater Visual SLAM with Depth Uncertainty and Medium Modeling: Rui Liu,

Sheng Fan,

Wenguan Wang,

Yi Yang; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2025_ICCV, author = {Liu, Rui and Fan, Sheng and Wang, Wenguan and Yang, Yi}, title = {Underwater Visual SLAM with Depth Uncertainty and Medium Modeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {970-980} }
Auxiliary Prompt Tuning of Vision-Language Models for Few-Shot Out-of-Distribution Detection: Wenjun Miao,

Guansong Pang,

Zihan Wang,

Jin Zheng,

Xiao Bai; [pdf]
[bibtex]
@InProceedings{Miao_2025_ICCV, author = {Miao, Wenjun and Pang, Guansong and Wang, Zihan and Zheng, Jin and Bai, Xiao}, title = {Auxiliary Prompt Tuning of Vision-Language Models for Few-Shot Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {4776-4785} }
ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting: Ruijie Zhu,

Mulin Yu,

Linning Xu,

Lihan Jiang,

Yixuan Li,

Tianzhu Zhang,

Jiangmiao Pang,

Bo Dai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2025_ICCV, author = {Zhu, Ruijie and Yu, Mulin and Xu, Linning and Jiang, Lihan and Li, Yixuan and Zhang, Tianzhu and Pang, Jiangmiao and Dai, Bo}, title = {ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {8350-8360} }; Back