Papers

Back

Unmixing Diffusion for Self-Supervised Hyperspectral Image Denoising
Haijin Zeng,
Jiezhang Cao,
Kai Zhang,
Yongyong Chen,
Hiep Luong,
Wilfried Philips
[pdf] [supp]
[bibtex]
@InProceedings{Zeng_2024_CVPR, author = {Zeng, Haijin and Cao, Jiezhang and Zhang, Kai and Chen, Yongyong and Luong, Hiep and Philips, Wilfried}, title = {Unmixing Diffusion for Self-Supervised Hyperspectral Image Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27820-27830} }

Test-Time Linear Out-of-Distribution Detection
Ke Fan,
Tong Liu,
Xingyu Qiu,
Yikai Wang,
Lian Huai,
Zeyu Shangguan,
Shuang Gou,
Fengjian Liu,
Yuqian Fu,
Yanwei Fu,
Xingqun Jiang
[pdf] [supp]
[bibtex]
@InProceedings{Fan_2024_CVPR, author = {Fan, Ke and Liu, Tong and Qiu, Xingyu and Wang, Yikai and Huai, Lian and Shangguan, Zeyu and Gou, Shuang and Liu, Fengjian and Fu, Yuqian and Fu, Yanwei and Jiang, Xingqun}, title = {Test-Time Linear Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23752-23761} }

Unsupervised Blind Image Deblurring Based on Self-Enhancement
Lufei Chen,
Xiangpeng Tian,
Shuhua Xiong,
Yinjie Lei,
Chao Ren
[pdf] [supp]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Lufei and Tian, Xiangpeng and Xiong, Shuhua and Lei, Yinjie and Ren, Chao}, title = {Unsupervised Blind Image Deblurring Based on Self-Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25691-25700} }

UFineBench: Towards Text-based Person Retrieval with Ultra-fine Granularity
Jialong Zuo,
Hanyu Zhou,
Ying Nie,
Feng Zhang,
Tianyu Guo,
Nong Sang,
Yunhe Wang,
Changxin Gao
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zuo_2024_CVPR, author = {Zuo, Jialong and Zhou, Hanyu and Nie, Ying and Zhang, Feng and Guo, Tianyu and Sang, Nong and Wang, Yunhe and Gao, Changxin}, title = {UFineBench: Towards Text-based Person Retrieval with Ultra-fine Granularity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22010-22019} }

Efficient Hyperparameter Optimization with Adaptive Fidelity Identification
Jiantong Jiang,
Zeyi Wen,
Atif Mansoor,
Ajmal Mian
[pdf] [supp]
[bibtex]
@InProceedings{Jiang_2024_CVPR, author = {Jiang, Jiantong and Wen, Zeyi and Mansoor, Atif and Mian, Ajmal}, title = {Efficient Hyperparameter Optimization with Adaptive Fidelity Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26181-26190} }

Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training
Qian Li,
Yuxiao Hu,
Yinpeng Dong,
Dongxiao Zhang,
Yuntian Chen
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Qian and Hu, Yuxiao and Dong, Yinpeng and Zhang, Dongxiao and Chen, Yuntian}, title = {Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24442-24451} }

GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model for Distortion-aware Panoramic Semantic Segmentation
Weiming Zhang,
Yexin Liu,
Xu Zheng,
Lin Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Weiming and Liu, Yexin and Zheng, Xu and Wang, Lin}, title = {GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model for Distortion-aware Panoramic Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28264-28273} }

DYSON: Dynamic Feature Space Self-Organization for Online Task-Free Class Incremental Learning
Yuhang He,
Yingjie Chen,
Yuhan Jin,
Songlin Dong,
Xing Wei,
Yihong Gong
[pdf] [supp]
[bibtex]
@InProceedings{He_2024_CVPR, author = {He, Yuhang and Chen, Yingjie and Jin, Yuhan and Dong, Songlin and Wei, Xing and Gong, Yihong}, title = {DYSON: Dynamic Feature Space Self-Organization for Online Task-Free Class Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23741-23751} }

Event-based Structure-from-Orbit
Ethan Elms,
Yasir Latif,
Tae Ha Park,
Tat-Jun Chin
[pdf] [arXiv]
[bibtex]
@InProceedings{Elms_2024_CVPR, author = {Elms, Ethan and Latif, Yasir and Park, Tae Ha and Chin, Tat-Jun}, title = {Event-based Structure-from-Orbit}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19541-19550} }

LED: A Large-scale Real-world Paired Dataset for Event Camera Denoising
Yuxing Duan
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Duan_2024_CVPR, author = {Duan, Yuxing}, title = {LED: A Large-scale Real-world Paired Dataset for Event Camera Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25637-25647} }

SVDinsTN: A Tensor Network Paradigm for Efficient Structure Search from Regularized Modeling Perspective
Yu-Bang Zheng,
Xi-Le Zhao,
Junhua Zeng,
Chao Li,
Qibin Zhao,
Heng-Chao Li,
Ting-Zhu Huang
[pdf] [arXiv]
[bibtex]
@InProceedings{Zheng_2024_CVPR, author = {Zheng, Yu-Bang and Zhao, Xi-Le and Zeng, Junhua and Li, Chao and Zhao, Qibin and Li, Heng-Chao and Huang, Ting-Zhu}, title = {SVDinsTN: A Tensor Network Paradigm for Efficient Structure Search from Regularized Modeling Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26254-26263} }

Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields
Haoyuan Wang,
Wenbo Hu,
Lei Zhu,
Rynson W.H. Lau
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Haoyuan and Hu, Wenbo and Zhu, Lei and Lau, Rynson W.H.}, title = {Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19999-20008} }

Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation
Xinyao Li,
Yuke Li,
Zhekai Du,
Fengling Li,
Ke Lu,
Jingjing Li
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Xinyao and Li, Yuke and Du, Zhekai and Li, Fengling and Lu, Ke and Li, Jingjing}, title = {Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23364-23374} }

Overcoming Generic Knowledge Loss with Selective Parameter Update
Wenxuan Zhang,
Paul Janson,
Rahaf Aljundi,
Mohamed Elhoseiny
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Wenxuan and Janson, Paul and Aljundi, Rahaf and Elhoseiny, Mohamed}, title = {Overcoming Generic Knowledge Loss with Selective Parameter Update}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24046-24056} }

Diff-BGM: A Diffusion Model for Video Background Music Generation
Sizhe Li,
Yiming Qin,
Minghang Zheng,
Xin Jin,
Yang Liu
[pdf] [supp]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Sizhe and Qin, Yiming and Zheng, Minghang and Jin, Xin and Liu, Yang}, title = {Diff-BGM: A Diffusion Model for Video Background Music Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27348-27357} }

Looking Similar Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning
Nikhil Singh,
Chih-Wei Wu,
Iroro Orife,
Mahdi Kalayeh
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Singh_2024_CVPR, author = {Singh, Nikhil and Wu, Chih-Wei and Orife, Iroro and Kalayeh, Mahdi}, title = {Looking Similar Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26907-26918} }

Towards HDR and HFR Video from Rolling-Mixed-Bit Spikings
Yakun Chang,
Yeliduosi Xiaokaiti,
Yujia Liu,
Bin Fan,
Zhaojun Huang,
Tiejun Huang,
Boxin Shi
[pdf] [supp]
[bibtex]
@InProceedings{Chang_2024_CVPR, author = {Chang, Yakun and Xiaokaiti, Yeliduosi and Liu, Yujia and Fan, Bin and Huang, Zhaojun and Huang, Tiejun and Shi, Boxin}, title = {Towards HDR and HFR Video from Rolling-Mixed-Bit Spikings}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25117-25127} }

Bridging the Synthetic-to-Authentic Gap: Distortion-Guided Unsupervised Domain Adaptation for Blind Image Quality Assessment
Aobo Li,
Jinjian Wu,
Yongxu Liu,
Leida Li
[pdf] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Aobo and Wu, Jinjian and Liu, Yongxu and Li, Leida}, title = {Bridging the Synthetic-to-Authentic Gap: Distortion-Guided Unsupervised Domain Adaptation for Blind Image Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28422-28431} }

Coherent Temporal Synthesis for Incremental Action Segmentation
Guodong Ding,
Hans Golong,
Angela Yao
[pdf] [arXiv]
[bibtex]
@InProceedings{Ding_2024_CVPR, author = {Ding, Guodong and Golong, Hans and Yao, Angela}, title = {Coherent Temporal Synthesis for Incremental Action Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28485-28494} }

HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting
Yuheng Jiang,
Zhehao Shen,
Penghao Wang,
Zhuo Su,
Yu Hong,
Yingliang Zhang,
Jingyi Yu,
Lan Xu
[pdf] [arXiv]
[bibtex]
@InProceedings{Jiang_2024_CVPR, author = {Jiang, Yuheng and Shen, Zhehao and Wang, Penghao and Su, Zhuo and Hong, Yu and Zhang, Yingliang and Yu, Jingyi and Xu, Lan}, title = {HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19734-19745} }

G-FARS: Gradient-Field-based Auto-Regressive Sampling for 3D Part Grouping
Junfeng Cheng,
Tania Stathaki
[pdf] [supp]
[bibtex]
@InProceedings{Cheng_2024_CVPR, author = {Cheng, Junfeng and Stathaki, Tania}, title = {G-FARS: Gradient-Field-based Auto-Regressive Sampling for 3D Part Grouping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27652-27661} }

DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning
Haoran Xu,
Peixi Peng,
Guang Tan,
Yuan Li,
Xinhai Xu,
Yonghong Tian
[pdf] [supp]
[bibtex]
@InProceedings{Xu_2024_CVPR, author = {Xu, Haoran and Peng, Peixi and Tan, Guang and Li, Yuan and Xu, Xinhai and Tian, Yonghong}, title = {DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26508-26518} }

DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models
Khawar Islam,
Muhammad Zaigham Zaheer,
Arif Mahmood,
Karthik Nandakumar
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Islam_2024_CVPR, author = {Islam, Khawar and Zaheer, Muhammad Zaigham and Mahmood, Arif and Nandakumar, Karthik}, title = {DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27621-27630} }

FREE: Faster and Better Data-Free Meta-Learning
Yongxian Wei,
Zixuan Hu,
Zhenyi Wang,
Li Shen,
Chun Yuan,
Dacheng Tao
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wei_2024_CVPR, author = {Wei, Yongxian and Hu, Zixuan and Wang, Zhenyi and Shen, Li and Yuan, Chun and Tao, Dacheng}, title = {FREE: Faster and Better Data-Free Meta-Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23273-23282} }

Bi-SSC: Geometric-Semantic Bidirectional Fusion for Camera-based 3D Semantic Scene Completion
Yujie Xue,
Ruihui Li,
Fan Wu,
Zhuo Tang,
Kenli Li,
Mingxing Duan
[pdf] [supp]
[bibtex]
@InProceedings{Xue_2024_CVPR, author = {Xue, Yujie and Li, Ruihui and Wu, Fan and Tang, Zhuo and Li, Kenli and Duan, Mingxing}, title = {Bi-SSC: Geometric-Semantic Bidirectional Fusion for Camera-based 3D Semantic Scene Completion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20124-20134} }

Parameter Efficient Self-Supervised Geospatial Domain Adaptation
Linus Scheibenreif,
Michael Mommert,
Damian Borth
[pdf] [supp]
[bibtex]
@InProceedings{Scheibenreif_2024_CVPR, author = {Scheibenreif, Linus and Mommert, Michael and Borth, Damian}, title = {Parameter Efficient Self-Supervised Geospatial Domain Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27841-27851} }

Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replay
Yuhang Zhou,
Zhongyun Hua
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2024_CVPR, author = {Zhou, Yuhang and Hua, Zhongyun}, title = {Defense without Forgetting: Continual Adversarial Defense with Anisotropic \& Isotropic Pseudo Replay}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24263-24272} }

Transferable Structural Sparse Adversarial Attack Via Exact Group Sparsity Training
Di Ming,
Peng Ren,
Yunlong Wang,
Xin Feng
[pdf] [supp]
[bibtex]
@InProceedings{Ming_2024_CVPR, author = {Ming, Di and Ren, Peng and Wang, Yunlong and Feng, Xin}, title = {Transferable Structural Sparse Adversarial Attack Via Exact Group Sparsity Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24696-24705} }

Unsupervised Occupancy Learning from Sparse Point Cloud
Amine Ouasfi,
Adnane Boukhayma
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ouasfi_2024_CVPR, author = {Ouasfi, Amine and Boukhayma, Adnane}, title = {Unsupervised Occupancy Learning from Sparse Point Cloud}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21729-21739} }

3DInAction: Understanding Human Actions in 3D Point Clouds
Yizhak Ben-Shabat,
Oren Shrout,
Stephen Gould
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ben-Shabat_2024_CVPR, author = {Ben-Shabat, Yizhak and Shrout, Oren and Gould, Stephen}, title = {3DInAction: Understanding Human Actions in 3D Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19978-19987} }

SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection
Junsu Kim,
Hoseong Cho,
Jihyeon Kim,
Yihalem Yimolal Tiruneh,
Seungryul Baek
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_CVPR, author = {Kim, Junsu and Cho, Hoseong and Kim, Jihyeon and Tiruneh, Yihalem Yimolal and Baek, Seungryul}, title = {SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28772-28781} }

Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving
Junhao Zheng,
Chenhao Lin,
Jiahao Sun,
Zhengyu Zhao,
Qian Li,
Chao Shen
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2024_CVPR, author = {Zheng, Junhao and Lin, Chenhao and Sun, Jiahao and Zhao, Zhengyu and Li, Qian and Shen, Chao}, title = {Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24452-24461} }

Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks
Shin'ya Yamaguchi,
Sekitoshi Kanai,
Kazuki Adachi,
Daiki Chijiwa
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yamaguchi_2024_CVPR, author = {Yamaguchi, Shin'ya and Kanai, Sekitoshi and Adachi, Kazuki and Chijiwa, Daiki}, title = {Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23481-23490} }

Multimodal Prompt Perceiver: Empower Adaptiveness Generalizability and Fidelity for All-in-One Image Restoration
Yuang Ai,
Huaibo Huang,
Xiaoqiang Zhou,
Jiexiang Wang,
Ran He
[pdf] [arXiv]
[bibtex]
@InProceedings{Ai_2024_CVPR, author = {Ai, Yuang and Huang, Huaibo and Zhou, Xiaoqiang and Wang, Jiexiang and He, Ran}, title = {Multimodal Prompt Perceiver: Empower Adaptiveness Generalizability and Fidelity for All-in-One Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25432-25444} }

Color Shift Estimation-and-Correction for Image Enhancement
Yiyu Li,
Ke Xu,
Gerhard Petrus Hancke,
Rynson W.H. Lau
[pdf] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Yiyu and Xu, Ke and Hancke, Gerhard Petrus and Lau, Rynson W.H.}, title = {Color Shift Estimation-and-Correction for Image Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25389-25398} }

Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network
Wenqiao Li,
Xiaohao Xu,
Yao Gu,
Bozhong Zheng,
Shenghua Gao,
Yingna Wu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Wenqiao and Xu, Xiaohao and Gu, Yao and Zheng, Bozhong and Gao, Shenghua and Wu, Yingna}, title = {Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22207-22216} }

Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications
Junyi Ma,
Xieyuanli Chen,
Jiawei Huang,
Jingyi Xu,
Zhen Luo,
Jintao Xu,
Weihao Gu,
Rui Ai,
Hesheng Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2024_CVPR, author = {Ma, Junyi and Chen, Xieyuanli and Huang, Jiawei and Xu, Jingyi and Luo, Zhen and Xu, Jintao and Gu, Weihao and Ai, Rui and Wang, Hesheng}, title = {Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21486-21495} }

DIEM: Decomposition-Integration Enhancing Multimodal Insights
Xinyi Jiang,
Guoming Wang,
Junhao Guo,
Juncheng Li,
Wenqiao Zhang,
Rongxing Lu,
Siliang Tang
[pdf]
[bibtex]
@InProceedings{Jiang_2024_CVPR, author = {Jiang, Xinyi and Wang, Guoming and Guo, Junhao and Li, Juncheng and Zhang, Wenqiao and Lu, Rongxing and Tang, Siliang}, title = {DIEM: Decomposition-Integration Enhancing Multimodal Insights}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27304-27313} }

Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment
Ziyu Shan,
Yujie Zhang,
Qi Yang,
Haichen Yang,
Yiling Xu,
Jenq-Neng Hwang,
Xiaozhong Xu,
Shan Liu
[pdf] [arXiv]
[bibtex]
@InProceedings{Shan_2024_CVPR, author = {Shan, Ziyu and Zhang, Yujie and Yang, Qi and Yang, Haichen and Xu, Yiling and Hwang, Jenq-Neng and Xu, Xiaozhong and Liu, Shan}, title = {Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25942-25951} }

Revisiting Spatial-Frequency Information Integration from a Hierarchical Perspective for Panchromatic and Multi-Spectral Image Fusion
Jiangtong Tan,
Jie Huang,
Naishan Zheng,
Man Zhou,
Keyu Yan,
Danfeng Hong,
Feng Zhao
[pdf] [supp]
[bibtex]
@InProceedings{Tan_2024_CVPR, author = {Tan, Jiangtong and Huang, Jie and Zheng, Naishan and Zhou, Man and Yan, Keyu and Hong, Danfeng and Zhao, Feng}, title = {Revisiting Spatial-Frequency Information Integration from a Hierarchical Perspective for Panchromatic and Multi-Spectral Image Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25922-25931} }

BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation
Jiahao Lu,
Jiacheng Deng,
Tianzhu Zhang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2024_CVPR, author = {Lu, Jiahao and Deng, Jiacheng and Zhang, Tianzhu}, title = {BSNet: Box-Supervised Simulation-assisted Mean Teacher for 3D Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20374-20384} }

Adaptive Slot Attention: Object Discovery with Dynamic Slot Number
Ke Fan,
Zechen Bai,
Tianjun Xiao,
Tong He,
Max Horn,
Yanwei Fu,
Francesco Locatello,
Zheng Zhang
[pdf] [supp]
[bibtex]
@InProceedings{Fan_2024_CVPR, author = {Fan, Ke and Bai, Zechen and Xiao, Tianjun and He, Tong and Horn, Max and Fu, Yanwei and Locatello, Francesco and Zhang, Zheng}, title = {Adaptive Slot Attention: Object Discovery with Dynamic Slot Number}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23062-23071} }

Task-Driven Wavelets using Constrained Empirical Risk Minimization
Eric Marcus,
Ray Sheombarsing,
Jan-Jakob Sonke,
Jonas Teuwen
[pdf] [supp]
[bibtex]
@InProceedings{Marcus_2024_CVPR, author = {Marcus, Eric and Sheombarsing, Ray and Sonke, Jan-Jakob and Teuwen, Jonas}, title = {Task-Driven Wavelets using Constrained Empirical Risk Minimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24098-24107} }

DeiT-LT: Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets
Harsh Rangwani,
Pradipto Mondal,
Mayank Mishra,
Ashish Ramayee Asokan,
R. Venkatesh Babu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rangwani_2024_CVPR, author = {Rangwani, Harsh and Mondal, Pradipto and Mishra, Mayank and Asokan, Ashish Ramayee and Babu, R. Venkatesh}, title = {DeiT-LT: Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23396-23406} }

FCS: Feature Calibration and Separation for Non-Exemplar Class Incremental Learning
Qiwei Li,
Yuxin Peng,
Jiahuan Zhou
[pdf] [supp]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Qiwei and Peng, Yuxin and Zhou, Jiahuan}, title = {FCS: Feature Calibration and Separation for Non-Exemplar Class Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28495-28504} }

Task2Box: Box Embeddings for Modeling Asymmetric Task Relationships
Rangel Daroya,
Aaron Sun,
Subhransu Maji
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Daroya_2024_CVPR, author = {Daroya, Rangel and Sun, Aaron and Maji, Subhransu}, title = {Task2Box: Box Embeddings for Modeling Asymmetric Task Relationships}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28827-28837} }

LoS: Local Structure-Guided Stereo Matching
Kunhong Li,
Longguang Wang,
Ye Zhang,
Kaiwen Xue,
Shunbo Zhou,
Yulan Guo
[pdf] [supp]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Kunhong and Wang, Longguang and Zhang, Ye and Xue, Kaiwen and Zhou, Shunbo and Guo, Yulan}, title = {LoS: Local Structure-Guided Stereo Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19746-19756} }

Probing the 3D Awareness of Visual Foundation Models
Mohamed El Banani,
Amit Raj,
Kevis-Kokitsi Maninis,
Abhishek Kar,
Yuanzhen Li,
Michael Rubinstein,
Deqing Sun,
Leonidas Guibas,
Justin Johnson,
Varun Jampani
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{El_Banani_2024_CVPR, author = {El Banani, Mohamed and Raj, Amit and Maninis, Kevis-Kokitsi and Kar, Abhishek and Li, Yuanzhen and Rubinstein, Michael and Sun, Deqing and Guibas, Leonidas and Johnson, Justin and Jampani, Varun}, title = {Probing the 3D Awareness of Visual Foundation Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21795-21806} }

When Visual Grounding Meets Gigapixel-level Large-scale Scenes: Benchmark and Approach
Tao Ma,
Bing Bai,
Haozhe Lin,
Heyuan Wang,
Yu Wang,
Lin Luo,
Lu Fang
[pdf] [supp]
[bibtex]
@InProceedings{Ma_2024_CVPR, author = {Ma, Tao and Bai, Bing and Lin, Haozhe and Wang, Heyuan and Wang, Yu and Luo, Lin and Fang, Lu}, title = {When Visual Grounding Meets Gigapixel-level Large-scale Scenes: Benchmark and Approach}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22119-22128} }

Mind Artist: Creating Artistic Snapshots with Human Thought
Jiaxuan Chen,
Yu Qi,
Yueming Wang,
Gang Pan
[pdf] [supp]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Jiaxuan and Qi, Yu and Wang, Yueming and Pan, Gang}, title = {Mind Artist: Creating Artistic Snapshots with Human Thought}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27207-27217} }

Accept the Modality Gap: An Exploration in the Hyperbolic Space
Sameera Ramasinghe,
Violetta Shevchenko,
Gil Avraham,
Ajanthan Thalaiyasingam
[pdf] [supp]
[bibtex]
@InProceedings{Ramasinghe_2024_CVPR, author = {Ramasinghe, Sameera and Shevchenko, Violetta and Avraham, Gil and Thalaiyasingam, Ajanthan}, title = {Accept the Modality Gap: An Exploration in the Hyperbolic Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27263-27272} }

Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation
Yuanhong Chen,
Yuyuan Liu,
Hu Wang,
Fengbei Liu,
Chong Wang,
Helen Frazer,
Gustavo Carneiro
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Yuanhong and Liu, Yuyuan and Wang, Hu and Liu, Fengbei and Wang, Chong and Frazer, Helen and Carneiro, Gustavo}, title = {Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26497-26507} }

Few-Shot Object Detection with Foundation Models
Guangxing Han,
Ser-Nam Lim
[pdf] [supp]
[bibtex]
@InProceedings{Han_2024_CVPR, author = {Han, Guangxing and Lim, Ser-Nam}, title = {Few-Shot Object Detection with Foundation Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28608-28618} }

FedMef: Towards Memory-efficient Federated Dynamic Pruning
Hong Huang,
Weiming Zhuang,
Chen Chen,
Lingjuan Lyu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2024_CVPR, author = {Huang, Hong and Zhuang, Weiming and Chen, Chen and Lyu, Lingjuan}, title = {FedMef: Towards Memory-efficient Federated Dynamic Pruning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27548-27557} }

PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization
Zining Chen,
Weiqiu Wang,
Zhicheng Zhao,
Fei Su,
Aidong Men,
Hongying Meng
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Zining and Wang, Weiqiu and Zhao, Zhicheng and Su, Fei and Men, Aidong and Meng, Hongying}, title = {PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23501-23511} }

SODA: Bottleneck Diffusion Models for Representation Learning
Drew A. Hudson,
Daniel Zoran,
Mateusz Malinowski,
Andrew K. Lampinen,
Andrew Jaegle,
James L. McClelland,
Loic Matthey,
Felix Hill,
Alexander Lerchner
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hudson_2024_CVPR, author = {Hudson, Drew A. and Zoran, Daniel and Malinowski, Mateusz and Lampinen, Andrew K. and Jaegle, Andrew and McClelland, James L. and Matthey, Loic and Hill, Felix and Lerchner, Alexander}, title = {SODA: Bottleneck Diffusion Models for Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23115-23127} }

Zero-Reference Low-Light Enhancement via Physical Quadruple Priors
Wenjing Wang,
Huan Yang,
Jianlong Fu,
Jiaying Liu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Wenjing and Yang, Huan and Fu, Jianlong and Liu, Jiaying}, title = {Zero-Reference Low-Light Enhancement via Physical Quadruple Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26057-26066} }

NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation
Sicheng Li,
Hao Li,
Yiyi Liao,
Lu Yu
[pdf] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Sicheng and Li, Hao and Liao, Yiyi and Yu, Lu}, title = {NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21274-21283} }

Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery
Mubashir Noman,
Muzammal Naseer,
Hisham Cholakkal,
Rao Muhammad Anwer,
Salman Khan,
Fahad Shahbaz Khan
[pdf] [arXiv]
[bibtex]
@InProceedings{Noman_2024_CVPR, author = {Noman, Mubashir and Naseer, Muzammal and Cholakkal, Hisham and Anwer, Rao Muhammad and Khan, Salman and Khan, Fahad Shahbaz}, title = {Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27811-27819} }

LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation
Kibum Kim,
Kanghoon Yoon,
Jaehyeong Jeon,
Yeonjun In,
Jinyoung Moon,
Donghyun Kim,
Chanyoung Park
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_CVPR, author = {Kim, Kibum and Yoon, Kanghoon and Jeon, Jaehyeong and In, Yeonjun and Moon, Jinyoung and Kim, Donghyun and Park, Chanyoung}, title = {LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28306-28316} }

Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling
Liwen Wu,
Sai Bi,
Zexiang Xu,
Fujun Luan,
Kai Zhang,
Iliyan Georgiev,
Kalyan Sunkavalli,
Ravi Ramamoorthi
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2024_CVPR, author = {Wu, Liwen and Bi, Sai and Xu, Zexiang and Luan, Fujun and Zhang, Kai and Georgiev, Iliyan and Sunkavalli, Kalyan and Ramamoorthi, Ravi}, title = {Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21157-21166} }

Label Propagation for Zero-shot Classification with Vision-Language Models
Vladan Stojni?,
Yannis Kalantidis,
Giorgos Tolias
[pdf] [supp]
[bibtex]
@InProceedings{Stojni?_2024_CVPR, author = {Stojni?, Vladan and Kalantidis, Yannis and Tolias, Giorgos}, title = {Label Propagation for Zero-shot Classification with Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23209-23218} }

Revisiting Global Translation Estimation with Feature Tracks
Peilin Tao,
Hainan Cui,
Mengqi Rong,
Shuhan Shen
[pdf] [supp]
[bibtex]
@InProceedings{Tao_2024_CVPR, author = {Tao, Peilin and Cui, Hainan and Rong, Mengqi and Shen, Shuhan}, title = {Revisiting Global Translation Estimation with Feature Tracks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20686-20696} }

Open-Set Domain Adaptation for Semantic Segmentation
Seun-An Choe,
Ah-Hyung Shin,
Keon-Hee Park,
Jinwoo Choi,
Gyeong-Moon Park
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Choe_2024_CVPR, author = {Choe, Seun-An and Shin, Ah-Hyung and Park, Keon-Hee and Choi, Jinwoo and Park, Gyeong-Moon}, title = {Open-Set Domain Adaptation for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23943-23953} }

Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training
Yipeng Gao,
Zeyu Wang,
Wei-Shi Zheng,
Cihang Xie,
Yuyin Zhou
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2024_CVPR, author = {Gao, Yipeng and Wang, Zeyu and Zheng, Wei-Shi and Xie, Cihang and Zhou, Yuyin}, title = {Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22998-23008} }

Probing Synergistic High-Order Interaction in Infrared and Visible Image Fusion
Naishan Zheng,
Man Zhou,
Jie Huang,
Junming Hou,
Haoying Li,
Yuan Xu,
Feng Zhao
[pdf]
[bibtex]
@InProceedings{Zheng_2024_CVPR, author = {Zheng, Naishan and Zhou, Man and Huang, Jie and Hou, Junming and Li, Haoying and Xu, Yuan and Zhao, Feng}, title = {Probing Synergistic High-Order Interaction in Infrared and Visible Image Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26384-26395} }

ESCAPE: Encoding Super-keypoints for Category-Agnostic Pose Estimation
Khoi Duc Nguyen,
Chen Li,
Gim Hee Lee
[pdf] [supp]
[bibtex]
@InProceedings{Nguyen_2024_CVPR, author = {Nguyen, Khoi Duc and Li, Chen and Lee, Gim Hee}, title = {ESCAPE: Encoding Super-keypoints for Category-Agnostic Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23491-23500} }

TULIP: Multi-camera 3D Precision Assessment of Parkinson's Disease
Kyungdo Kim,
Sihan Lyu,
Sneha Mantri,
Timothy W. Dunn
[pdf] [supp]
[bibtex]
@InProceedings{Kim_2024_CVPR, author = {Kim, Kyungdo and Lyu, Sihan and Mantri, Sneha and Dunn, Timothy W.}, title = {TULIP: Multi-camera 3D Precision Assessment of Parkinson's Disease}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22551-22562} }

HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces
Haithem Turki,
Vasu Agrawal,
Samuel Rota Bulò,
Lorenzo Porzi,
Peter Kontschieder,
Deva Ramanan,
Michael Zollhöfer,
Christian Richardt
[pdf] [supp]
[bibtex]
@InProceedings{Turki_2024_CVPR, author = {Turki, Haithem and Agrawal, Vasu and Bul\`o, Samuel Rota and Porzi, Lorenzo and Kontschieder, Peter and Ramanan, Deva and Zollh\"ofer, Michael and Richardt, Christian}, title = {HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19647-19656} }

Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring
Chengxu Liu,
Xuan Wang,
Xiangyu Xu,
Ruhao Tian,
Shuai Li,
Xueming Qian,
Ming-Hsuan Yang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Chengxu and Wang, Xuan and Xu, Xiangyu and Tian, Ruhao and Li, Shuai and Qian, Xueming and Yang, Ming-Hsuan}, title = {Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25595-25605} }

DART: Implicit Doppler Tomography for Radar Novel View Synthesis
Tianshu Huang,
John Miller,
Akarsh Prabhakara,
Tao Jin,
Tarana Laroia,
Zico Kolter,
Anthony Rowe
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2024_CVPR, author = {Huang, Tianshu and Miller, John and Prabhakara, Akarsh and Jin, Tao and Laroia, Tarana and Kolter, Zico and Rowe, Anthony}, title = {DART: Implicit Doppler Tomography for Radar Novel View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24118-24129} }

Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal
Yijun Yang,
Hongtao Wu,
Angelica I. Aviles-Rivero,
Yulun Zhang,
Jing Qin,
Lei Zhu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2024_CVPR, author = {Yang, Yijun and Wu, Hongtao and Aviles-Rivero, Angelica I. and Zhang, Yulun and Qin, Jing and Zhu, Lei}, title = {Genuine Knowledge from Practice: Diffusion Test-Time Adaptation for Video Adverse Weather Removal}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25606-25616} }

Gradient-based Parameter Selection for Efficient Fine-Tuning
Zhi Zhang,
Qizhe Zhang,
Zijun Gao,
Renrui Zhang,
Ekaterina Shutova,
Shiji Zhou,
Shanghang Zhang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Zhi and Zhang, Qizhe and Gao, Zijun and Zhang, Renrui and Shutova, Ekaterina and Zhou, Shiji and Zhang, Shanghang}, title = {Gradient-based Parameter Selection for Efficient Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28566-28577} }

Domain Prompt Learning with Quaternion Networks
Qinglong Cao,
Zhengqin Xu,
Yuntian Chen,
Chao Ma,
Xiaokang Yang
[pdf] [arXiv]
[bibtex]
@InProceedings{Cao_2024_CVPR, author = {Cao, Qinglong and Xu, Zhengqin and Chen, Yuntian and Ma, Chao and Yang, Xiaokang}, title = {Domain Prompt Learning with Quaternion Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26637-26646} }

BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation
Yunhao Ge,
Yihe Tang,
Jiashu Xu,
Cem Gokmen,
Chengshu Li,
Wensi Ai,
Benjamin Jose Martinez,
Arman Aydin,
Mona Anvari,
Ayush K Chakravarthy,
Hong-Xing Yu,
Josiah Wong,
Sanjana Srivastava,
Sharon Lee,
Shengxin Zha,
Laurent Itti,
Yunzhu Li,
Roberto Martín-Martín,
Miao Liu,
Pengchuan Zhang,
Ruohan Zhang,
Li Fei-Fei,
Jiajun Wu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ge_2024_CVPR, author = {Ge, Yunhao and Tang, Yihe and Xu, Jiashu and Gokmen, Cem and Li, Chengshu and Ai, Wensi and Martinez, Benjamin Jose and Aydin, Arman and Anvari, Mona and Chakravarthy, Ayush K and Yu, Hong-Xing and Wong, Josiah and Srivastava, Sanjana and Lee, Sharon and Zha, Shengxin and Itti, Laurent and Li, Yunzhu and Mart{\'\i}n-Mart{\'\i}n, Roberto and Liu, Miao and Zhang, Pengchuan and Zhang, Ruohan and Fei-Fei, Li and Wu, Jiajun}, title = {BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22401-22412} }

Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particle
Youtian Lin,
Zuozhuo Dai,
Siyu Zhu,
Yao Yao
[pdf] [supp]
[bibtex]
@InProceedings{Lin_2024_CVPR, author = {Lin, Youtian and Dai, Zuozhuo and Zhu, Siyu and Yao, Yao}, title = {Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particle}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21136-21145} }

DiVAS: Video and Audio Synchronization with Dynamic Frame Rates
Clara Fernandez-Labrador,
Mertcan Akçay,
Eitan Abecassis,
Joan Massich,
Christopher Schroers
[pdf]
[bibtex]
@InProceedings{Fernandez-Labrador_2024_CVPR, author = {Fernandez-Labrador, Clara and Ak\c{c}ay, Mertcan and Abecassis, Eitan and Massich, Joan and Schroers, Christopher}, title = {DiVAS: Video and Audio Synchronization with Dynamic Frame Rates}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26846-26854} }

HDRFlow: Real-Time HDR Video Reconstruction with Large Motions
Gangwei Xu,
Yujin Wang,
Jinwei Gu,
Tianfan Xue,
Xin Yang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2024_CVPR, author = {Xu, Gangwei and Wang, Yujin and Gu, Jinwei and Xue, Tianfan and Yang, Xin}, title = {HDRFlow: Real-Time HDR Video Reconstruction with Large Motions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24851-24860} }

SPIDeRS: Structured Polarization for Invisible Depth and Reflectance Sensing
Tomoki Ichikawa,
Shohei Nobuhara,
Ko Nishino
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ichikawa_2024_CVPR, author = {Ichikawa, Tomoki and Nobuhara, Shohei and Nishino, Ko}, title = {SPIDeRS: Structured Polarization for Invisible Depth and Reflectance Sensing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25077-25085} }

SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration
Xu Cao,
Takafumi Taketomi
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2024_CVPR, author = {Cao, Xu and Taketomi, Takafumi}, title = {SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20581-20590} }

ADFactory: An Effective Framework for Generalizing Optical Flow with NeRF
Han Ling,
Quansen Sun,
Yinghui Sun,
Xian Xu,
Xinfeng Li
[pdf] [supp]
[bibtex]
@InProceedings{Ling_2024_CVPR, author = {Ling, Han and Sun, Quansen and Sun, Yinghui and Xu, Xian and Li, Xinfeng}, title = {ADFactory: An Effective Framework for Generalizing Optical Flow with NeRF}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20591-20600} }

How Far Can We Compress Instant-NGP-Based NeRF?
Yihang Chen,
Qianyi Wu,
Mehrtash Harandi,
Jianfei Cai
[pdf] [supp]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Yihang and Wu, Qianyi and Harandi, Mehrtash and Cai, Jianfei}, title = {How Far Can We Compress Instant-NGP-Based NeRF?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20321-20330} }

GPT4Point: A Unified Framework for Point-Language Understanding and Generation
Zhangyang Qi,
Ye Fang,
Zeyi Sun,
Xiaoyang Wu,
Tong Wu,
Jiaqi Wang,
Dahua Lin,
Hengshuang Zhao
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qi_2024_CVPR, author = {Qi, Zhangyang and Fang, Ye and Sun, Zeyi and Wu, Xiaoyang and Wu, Tong and Wang, Jiaqi and Lin, Dahua and Zhao, Hengshuang}, title = {GPT4Point: A Unified Framework for Point-Language Understanding and Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26417-26427} }

SemCity: Semantic Scene Generation with Triplane Diffusion
Jumin Lee,
Sebin Lee,
Changho Jo,
Woobin Im,
Juhyeong Seon,
Sung-Eui Yoon
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2024_CVPR, author = {Lee, Jumin and Lee, Sebin and Jo, Changho and Im, Woobin and Seon, Juhyeong and Yoon, Sung-Eui}, title = {SemCity: Semantic Scene Generation with Triplane Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28337-28347} }

Improving Semantic Correspondence with Viewpoint-Guided Spherical Maps
Octave Mariotti,
Oisin Mac Aodha,
Hakan Bilen
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mariotti_2024_CVPR, author = {Mariotti, Octave and Mac Aodha, Oisin and Bilen, Hakan}, title = {Improving Semantic Correspondence with Viewpoint-Guided Spherical Maps}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19521-19530} }

Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models
Yabin Zhang,
Wenjie Zhu,
Hui Tang,
Zhiyuan Ma,
Kaiyang Zhou,
Lei Zhang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Yabin and Zhu, Wenjie and Tang, Hui and Ma, Zhiyuan and Zhou, Kaiyang and Zhang, Lei}, title = {Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28718-28728} }

LION: Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge
Gongwei Chen,
Leyang Shen,
Rui Shao,
Xiang Deng,
Liqiang Nie
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Gongwei and Shen, Leyang and Shao, Rui and Deng, Xiang and Nie, Liqiang}, title = {LION: Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26540-26550} }

Learning to Select Views for Efficient Multi-View Understanding
Yunzhong Hou,
Stephen Gould,
Liang Zheng
[pdf] [supp]
[bibtex]
@InProceedings{Hou_2024_CVPR, author = {Hou, Yunzhong and Gould, Stephen and Zheng, Liang}, title = {Learning to Select Views for Efficient Multi-View Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20135-20144} }

Unified Entropy Optimization for Open-Set Test-Time Adaptation
Zhengqing Gao,
Xu-Yao Zhang,
Cheng-Lin Liu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2024_CVPR, author = {Gao, Zhengqing and Zhang, Xu-Yao and Liu, Cheng-Lin}, title = {Unified Entropy Optimization for Open-Set Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23975-23984} }

Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning
Da-Wei Zhou,
Hai-Long Sun,
Han-Jia Ye,
De-Chuan Zhan
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2024_CVPR, author = {Zhou, Da-Wei and Sun, Hai-Long and Ye, Han-Jia and Zhan, De-Chuan}, title = {Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23554-23564} }

L4D-Track: Language-to-4D Modeling Towards 6-DoF Tracking and Shape Reconstruction in 3D Point Cloud Stream
Jingtao Sun,
Yaonan Wang,
Mingtao Feng,
Yulan Guo,
Ajmal Mian,
Mike Zheng Shou
[pdf] [supp]
[bibtex]
@InProceedings{Sun_2024_CVPR, author = {Sun, Jingtao and Wang, Yaonan and Feng, Mingtao and Guo, Yulan and Mian, Ajmal and Shou, Mike Zheng}, title = {L4D-Track: Language-to-4D Modeling Towards 6-DoF Tracking and Shape Reconstruction in 3D Point Cloud Stream}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21146-21156} }

General Point Model Pretraining with Autoencoding and Autoregressive
Zhe Li,
Zhangyang Gao,
Cheng Tan,
Bocheng Ren,
Laurence T. Yang,
Stan Z. Li
[pdf] [supp]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Zhe and Gao, Zhangyang and Tan, Cheng and Ren, Bocheng and Yang, Laurence T. and Li, Stan Z.}, title = {General Point Model Pretraining with Autoencoding and Autoregressive}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20954-20964} }

MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures
Zhangyang Xiong,
Chenghong Li,
Kenkun Liu,
Hongjie Liao,
Jianqiao Hu,
Junyi Zhu,
Shuliang Ning,
Lingteng Qiu,
Chongjie Wang,
Shijie Wang,
Shuguang Cui,
Xiaoguang Han
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiong_2024_CVPR, author = {Xiong, Zhangyang and Li, Chenghong and Liu, Kenkun and Liao, Hongjie and Hu, Jianqiao and Zhu, Junyi and Ning, Shuliang and Qiu, Lingteng and Wang, Chongjie and Wang, Shijie and Cui, Shuguang and Han, Xiaoguang}, title = {MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19801-19811} }

NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Models
Yusuf Dalva,
Pinar Yanardag
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dalva_2024_CVPR, author = {Dalva, Yusuf and Yanardag, Pinar}, title = {NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24209-24218} }

SpecNeRF: Gaussian Directional Encoding for Specular Reflections
Li Ma,
Vasu Agrawal,
Haithem Turki,
Changil Kim,
Chen Gao,
Pedro Sander,
Michael Zollhöfer,
Christian Richardt
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2024_CVPR, author = {Ma, Li and Agrawal, Vasu and Turki, Haithem and Kim, Changil and Gao, Chen and Sander, Pedro and Zollh\"ofer, Michael and Richardt, Christian}, title = {SpecNeRF: Gaussian Directional Encoding for Specular Reflections}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21188-21198} }

Snapshot Lidar: Fourier Embedding of Amplitude and Phase for Single-Image Depth Reconstruction
Sarah Friday,
Yunzi Shi,
Yaswanth Cherivirala,
Vishwanath Saragadam,
Adithya Pediredla
[pdf] [supp]
[bibtex]
@InProceedings{Friday_2024_CVPR, author = {Friday, Sarah and Shi, Yunzi and Cherivirala, Yaswanth and Saragadam, Vishwanath and Pediredla, Adithya}, title = {Snapshot Lidar: Fourier Embedding of Amplitude and Phase for Single-Image Depth Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25203-25212} }

Convolutional Prompting meets Language Models for Continual Learning
Anurag Roy,
Riddhiman Moulick,
Vinay K. Verma,
Saptarshi Ghosh,
Abir Das
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Roy_2024_CVPR, author = {Roy, Anurag and Moulick, Riddhiman and Verma, Vinay K. and Ghosh, Saptarshi and Das, Abir}, title = {Convolutional Prompting meets Language Models for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23616-23626} }

Distilling Semantic Priors from SAM to Efficient Image Restoration Models
Quan Zhang,
Xiaoyu Liu,
Wei Li,
Hanting Chen,
Junchao Liu,
Jie Hu,
Zhiwei Xiong,
Chun Yuan,
Yunhe Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Quan and Liu, Xiaoyu and Li, Wei and Chen, Hanting and Liu, Junchao and Hu, Jie and Xiong, Zhiwei and Yuan, Chun and Wang, Yunhe}, title = {Distilling Semantic Priors from SAM to Efficient Image Restoration Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25409-25419} }

Learning Intra-view and Cross-view Geometric Knowledge for Stereo Matching
Rui Gong,
Weide Liu,
Zaiwang Gu,
Xulei Yang,
Jun Cheng
[pdf] [arXiv]
[bibtex]
@InProceedings{Gong_2024_CVPR, author = {Gong, Rui and Liu, Weide and Gu, Zaiwang and Yang, Xulei and Cheng, Jun}, title = {Learning Intra-view and Cross-view Geometric Knowledge for Stereo Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20752-20762} }

Rethinking the Evaluation Protocol of Domain Generalization
Han Yu,
Xingxuan Zhang,
Renzhe Xu,
Jiashuo Liu,
Yue He,
Peng Cui
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2024_CVPR, author = {Yu, Han and Zhang, Xingxuan and Xu, Renzhe and Liu, Jiashuo and He, Yue and Cui, Peng}, title = {Rethinking the Evaluation Protocol of Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21897-21908} }

Aligning Logits Generatively for Principled Black-Box Knowledge Distillation
Jing Ma,
Xiang Xiang,
Ke Wang,
Yuchuan Wu,
Yongbin Li
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2024_CVPR, author = {Ma, Jing and Xiang, Xiang and Wang, Ke and Wu, Yuchuan and Li, Yongbin}, title = {Aligning Logits Generatively for Principled Black-Box Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23148-23157} }

HoloVIC: Large-scale Dataset and Benchmark for Multi-Sensor Holographic Intersection and Vehicle-Infrastructure Cooperative
Cong Ma,
Lei Qiao,
Chengkai Zhu,
Kai Liu,
Zelong Kong,
Qing Li,
Xueqi Zhou,
Yuheng Kan,
Wei Wu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2024_CVPR, author = {Ma, Cong and Qiao, Lei and Zhu, Chengkai and Liu, Kai and Kong, Zelong and Li, Qing and Zhou, Xueqi and Kan, Yuheng and Wu, Wei}, title = {HoloVIC: Large-scale Dataset and Benchmark for Multi-Sensor Holographic Intersection and Vehicle-Infrastructure Cooperative}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22129-22138} }

LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
Siyuan Cheng,
Guanhong Tao,
Yingqi Liu,
Guangyu Shen,
Shengwei An,
Shiwei Feng,
Xiangzhe Xu,
Kaiyuan Zhang,
Shiqing Ma,
Xiangyu Zhang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2024_CVPR, author = {Cheng, Siyuan and Tao, Guanhong and Liu, Yingqi and Shen, Guangyu and An, Shengwei and Feng, Shiwei and Xu, Xiangzhe and Zhang, Kaiyuan and Ma, Shiqing and Zhang, Xiangyu}, title = {LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24798-24809} }

LAN: Learning to Adapt Noise for Image Denoising
Changjin Kim,
Tae Hyun Kim,
Sungyong Baik
[pdf] [supp]
[bibtex]
@InProceedings{Kim_2024_CVPR, author = {Kim, Changjin and Kim, Tae Hyun and Baik, Sungyong}, title = {LAN: Learning to Adapt Noise for Image Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25193-25202} }

HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes
Yichen Yao,
Zimo Jiang,
Yujing Sun,
Zhencai Zhu,
Xinge Zhu,
Runnan Chen,
Yuexin Ma
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yao_2024_CVPR, author = {Yao, Yichen and Jiang, Zimo and Sun, Yujing and Zhu, Zhencai and Zhu, Xinge and Chen, Runnan and Ma, Yuexin}, title = {HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28120-28129} }

Improving Transferable Targeted Adversarial Attacks with Model Self-Enhancement
Han Wu,
Guanyan Ou,
Weibin Wu,
Zibin Zheng
[pdf]
[bibtex]
@InProceedings{Wu_2024_CVPR, author = {Wu, Han and Ou, Guanyan and Wu, Weibin and Zheng, Zibin}, title = {Improving Transferable Targeted Adversarial Attacks with Model Self-Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24615-24624} }

Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos
Leonhard Sommer,
Artur Jesslen,
Eddy Ilg,
Adam Kortylewski
[pdf] [supp]
[bibtex]
@InProceedings{Sommer_2024_CVPR, author = {Sommer, Leonhard and Jesslen, Artur and Ilg, Eddy and Kortylewski, Adam}, title = {Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22787-22796} }

FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations
Christian Diller,
Thomas Funkhouser,
Angela Dai
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Diller_2024_CVPR, author = {Diller, Christian and Funkhouser, Thomas and Dai, Angela}, title = {FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19902-19914} }

NightCC: Nighttime Color Constancy via Adaptive Channel Masking
Shuwei Li,
Robby T. Tan
[pdf]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Shuwei and Tan, Robby T.}, title = {NightCC: Nighttime Color Constancy via Adaptive Channel Masking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25522-25531} }

UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes
David Rozenberszki,
Or Litany,
Angela Dai
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rozenberszki_2024_CVPR, author = {Rozenberszki, David and Litany, Or and Dai, Angela}, title = {UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19957-19967} }

Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks
Boheng Li,
Yishuo Cai,
Haowei Li,
Feng Xue,
Zhifeng Li,
Yiming Li
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Boheng and Cai, Yishuo and Li, Haowei and Xue, Feng and Li, Zhifeng and Li, Yiming}, title = {Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24523-24533} }

A Simple Recipe for Language-guided Domain Generalized Segmentation
Mohammad Fahes,
Tuan-Hung Vu,
Andrei Bursuc,
Patrick Pérez,
Raoul de Charette
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fahes_2024_CVPR, author = {Fahes, Mohammad and Vu, Tuan-Hung and Bursuc, Andrei and P\'erez, Patrick and de Charette, Raoul}, title = {A Simple Recipe for Language-guided Domain Generalized Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23428-23437} }

Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset
Yiming Li,
Zhiheng Li,
Nuo Chen,
Moonjun Gong,
Zonglin Lyu,
Zehong Wang,
Peili Jiang,
Chen Feng
[pdf]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Yiming and Li, Zhiheng and Chen, Nuo and Gong, Moonjun and Lyu, Zonglin and Wang, Zehong and Jiang, Peili and Feng, Chen}, title = {Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22041-22051} }

From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers
Swaminathan Gurumurthy,
Karnik Ram,
Bingqing Chen,
Zachary Manchester,
Zico Kolter
[pdf] [supp]
[bibtex]
@InProceedings{Gurumurthy_2024_CVPR, author = {Gurumurthy, Swaminathan and Ram, Karnik and Chen, Bingqing and Manchester, Zachary and Kolter, Zico}, title = {From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27507-27516} }

Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation
Ji-Jia Wu,
Andy Chia-Hao Chang,
Chieh-Yu Chuang,
Chun-Pei Chen,
Yu-Lun Liu,
Min-Hung Chen,
Hou-Ning Hu,
Yung-Yu Chuang,
Yen-Yu Lin
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2024_CVPR, author = {Wu, Ji-Jia and Chang, Andy Chia-Hao and Chuang, Chieh-Yu and Chen, Chun-Pei and Liu, Yu-Lun and Chen, Min-Hung and Hu, Hou-Ning and Chuang, Yung-Yu and Lin, Yen-Yu}, title = {Image-Text Co-Decomposition for Text-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26794-26803} }

Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation
Hongwei Yan,
Liyuan Wang,
Kaisheng Ma,
Yi Zhong
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yan_2024_CVPR, author = {Yan, Hongwei and Wang, Liyuan and Ma, Kaisheng and Zhong, Yi}, title = {Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23670-23680} }

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange
Yanhao Wu,
Tong Zhang,
Wei Ke,
Congpei Qiu,
Sabine Süsstrunk,
Mathieu Salzmann
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2024_CVPR, author = {Wu, Yanhao and Zhang, Tong and Ke, Wei and Qiu, Congpei and S\"usstrunk, Sabine and Salzmann, Mathieu}, title = {Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23052-23061} }

Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models
Daniel Geng,
Inbum Park,
Andrew Owens
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Geng_2024_CVPR, author = {Geng, Daniel and Park, Inbum and Owens, Andrew}, title = {Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24154-24163} }

Leveraging Predicate and Triplet Learning for Scene Graph Generation
Jiankai Li,
Yunhong Wang,
Xiefan Guo,
Ruijie Yang,
Weixin Li
[pdf] [supp]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Jiankai and Wang, Yunhong and Guo, Xiefan and Yang, Ruijie and Li, Weixin}, title = {Leveraging Predicate and Triplet Learning for Scene Graph Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28369-28379} }

CoDi-2: In-Context Interleaved and Interactive Any-to-Any Generation
Zineng Tang,
Ziyi Yang,
Mahmoud Khademi,
Yang Liu,
Chenguang Zhu,
Mohit Bansal
[pdf] [supp]
[bibtex]
@InProceedings{Tang_2024_CVPR, author = {Tang, Zineng and Yang, Ziyi and Khademi, Mahmoud and Liu, Yang and Zhu, Chenguang and Bansal, Mohit}, title = {CoDi-2: In-Context Interleaved and Interactive Any-to-Any Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27425-27434} }

Tuning Stable Rank Shrinkage: Aiming at the Overlooked Structural Risk in Fine-tuning
Sicong Shen,
Yang Zhou,
Bingzheng Wei,
Eric I-Chao Chang,
Yan Xu
[pdf] [supp]
[bibtex]
@InProceedings{Shen_2024_CVPR, author = {Shen, Sicong and Zhou, Yang and Wei, Bingzheng and Chang, Eric I-Chao and Xu, Yan}, title = {Tuning Stable Rank Shrinkage: Aiming at the Overlooked Structural Risk in Fine-tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28474-28484} }

Towards Automatic Power Battery Detection: New Challenge Benchmark Dataset and Baseline
Xiaoqi Zhao,
Youwei Pang,
Zhenyu Chen,
Qian Yu,
Lihe Zhang,
Hanqi Liu,
Jiaming Zuo,
Huchuan Lu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2024_CVPR, author = {Zhao, Xiaoqi and Pang, Youwei and Chen, Zhenyu and Yu, Qian and Zhang, Lihe and Liu, Hanqi and Zuo, Jiaming and Lu, Huchuan}, title = {Towards Automatic Power Battery Detection: New Challenge Benchmark Dataset and Baseline}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22020-22029} }

AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection
Trevine Oorloff,
Surya Koppisetti,
Nicolò Bonettini,
Divyaraj Solanki,
Ben Colman,
Yaser Yacoob,
Ali Shahriyari,
Gaurav Bharaj
[pdf] [supp]
[bibtex]
@InProceedings{Oorloff_2024_CVPR, author = {Oorloff, Trevine and Koppisetti, Surya and Bonettini, Nicol\`o and Solanki, Divyaraj and Colman, Ben and Yacoob, Yaser and Shahriyari, Ali and Bharaj, Gaurav}, title = {AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27102-27112} }

X-MIC: Cross-Modal Instance Conditioning for Egocentric Action Generalization
Anna Kukleva,
Fadime Sener,
Edoardo Remelli,
Bugra Tekin,
Eric Sauser,
Bernt Schiele,
Shugao Ma
[pdf] [supp]
[bibtex]
@InProceedings{Kukleva_2024_CVPR, author = {Kukleva, Anna and Sener, Fadime and Remelli, Edoardo and Tekin, Bugra and Sauser, Eric and Schiele, Bernt and Ma, Shugao}, title = {X-MIC: Cross-Modal Instance Conditioning for Egocentric Action Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26364-26373} }

AV-RIR: Audio-Visual Room Impulse Response Estimation
Anton Ratnarajah,
Sreyan Ghosh,
Sonal Kumar,
Purva Chiniya,
Dinesh Manocha
[pdf] [supp]
[bibtex]
@InProceedings{Ratnarajah_2024_CVPR, author = {Ratnarajah, Anton and Ghosh, Sreyan and Kumar, Sonal and Chiniya, Purva and Manocha, Dinesh}, title = {AV-RIR: Audio-Visual Room Impulse Response Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27164-27175} }

Dual-Consistency Model Inversion for Non-Exemplar Class Incremental Learning
Zihuan Qiu,
Yi Xu,
Fanman Meng,
Hongliang Li,
Linfeng Xu,
Qingbo Wu
[pdf] [supp]
[bibtex]
@InProceedings{Qiu_2024_CVPR, author = {Qiu, Zihuan and Xu, Yi and Meng, Fanman and Li, Hongliang and Xu, Linfeng and Wu, Qingbo}, title = {Dual-Consistency Model Inversion for Non-Exemplar Class Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24025-24035} }

Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers
Sheng Yang,
Jiawang Bai,
Kuofeng Gao,
Yong Yang,
Yiming Li,
Shu-Tao Xia
[pdf] [supp]
[bibtex]
@InProceedings{Yang_2024_CVPR, author = {Yang, Sheng and Bai, Jiawang and Gao, Kuofeng and Yang, Yong and Li, Yiming and Xia, Shu-Tao}, title = {Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24431-24441} }

PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization
Xu Peng,
Junwei Zhu,
Boyuan Jiang,
Ying Tai,
Donghao Luo,
Jiangning Zhang,
Wei Lin,
Taisong Jin,
Chengjie Wang,
Rongrong Ji
[pdf] [arXiv]
[bibtex]
@InProceedings{Peng_2024_CVPR, author = {Peng, Xu and Zhu, Junwei and Jiang, Boyuan and Tai, Ying and Luo, Donghao and Zhang, Jiangning and Lin, Wei and Jin, Taisong and Wang, Chengjie and Ji, Rongrong}, title = {PortraitBooth: A Versatile Portrait Model for Fast Identity-preserved Personalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27080-27090} }

Learn from View Correlation: An Anchor Enhancement Strategy for Multi-view Clustering
Suyuan Liu,
Ke Liang,
Zhibin Dong,
Siwei Wang,
Xihong Yang,
Sihang Zhou,
En Zhu,
Xinwang Liu
[pdf] [supp]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Suyuan and Liang, Ke and Dong, Zhibin and Wang, Siwei and Yang, Xihong and Zhou, Sihang and Zhu, En and Liu, Xinwang}, title = {Learn from View Correlation: An Anchor Enhancement Strategy for Multi-view Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26151-26161} }

APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation
Weizhao He,
Yang Zhang,
Wei Zhuo,
Linlin Shen,
Jiaqi Yang,
Songhe Deng,
Liang Sun
[pdf] [supp]
[bibtex]
@InProceedings{He_2024_CVPR, author = {He, Weizhao and Zhang, Yang and Zhuo, Wei and Shen, Linlin and Yang, Jiaqi and Deng, Songhe and Sun, Liang}, title = {APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23762-23772} }

Enhancing Visual Continual Learning with Language-Guided Supervision
Bolin Ni,
Hongbo Zhao,
Chenghao Zhang,
Ke Hu,
Gaofeng Meng,
Zhaoxiang Zhang,
Shiming Xiang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ni_2024_CVPR, author = {Ni, Bolin and Zhao, Hongbo and Zhang, Chenghao and Hu, Ke and Meng, Gaofeng and Zhang, Zhaoxiang and Xiang, Shiming}, title = {Enhancing Visual Continual Learning with Language-Guided Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24068-24077} }

Revamping Federated Learning Security from a Defender's Perspective: A Unified Defense with Homomorphic Encrypted Data Space
K Naveen Kumar,
Reshmi Mitra,
C Krishna Mohan
[pdf] [supp]
[bibtex]
@InProceedings{Kumar_2024_CVPR, author = {Kumar, K Naveen and Mitra, Reshmi and Mohan, C Krishna}, title = {Revamping Federated Learning Security from a Defender's Perspective: A Unified Defense with Homomorphic Encrypted Data Space}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24387-24397} }

A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution
Zhixiong Yang,
Jingyuan Xia,
Shengxi Li,
Xinghua Huang,
Shuanghui Zhang,
Zhen Liu,
Yaowen Fu,
Yongxiang Liu
[pdf] [arXiv]
[bibtex]
@InProceedings{Yang_2024_CVPR, author = {Yang, Zhixiong and Xia, Jingyuan and Li, Shengxi and Huang, Xinghua and Zhang, Shuanghui and Liu, Zhen and Fu, Yaowen and Liu, Yongxiang}, title = {A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26046-26056} }

Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning
Zihua Zhao,
Mengxi Chen,
Tianjie Dai,
Jiangchao Yao,
Bo Han,
Ya Zhang,
Yanfeng Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2024_CVPR, author = {Zhao, Zihua and Chen, Mengxi and Dai, Tianjie and Yao, Jiangchao and Han, Bo and Zhang, Ya and Wang, Yanfeng}, title = {Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27381-27390} }

DVMNet: Computing Relative Pose for Unseen Objects Beyond Hypotheses
Chen Zhao,
Tong Zhang,
Zheng Dang,
Mathieu Salzmann
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2024_CVPR, author = {Zhao, Chen and Zhang, Tong and Dang, Zheng and Salzmann, Mathieu}, title = {DVMNet: Computing Relative Pose for Unseen Objects Beyond Hypotheses}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20485-20495} }

MuRF: Multi-Baseline Radiance Fields
Haofei Xu,
Anpei Chen,
Yuedong Chen,
Christos Sakaridis,
Yulun Zhang,
Marc Pollefeys,
Andreas Geiger,
Fisher Yu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2024_CVPR, author = {Xu, Haofei and Chen, Anpei and Chen, Yuedong and Sakaridis, Christos and Zhang, Yulun and Pollefeys, Marc and Geiger, Andreas and Yu, Fisher}, title = {MuRF: Multi-Baseline Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20041-20050} }

Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincare Ball
Simon Weber,
Bar?? Zöngür,
Nikita Araslanov,
Daniel Cremers
[pdf] [supp]
[bibtex]
@InProceedings{Weber_2024_CVPR, author = {Weber, Simon and Z\"ong\"ur, Bar?? and Araslanov, Nikita and Cremers, Daniel}, title = {Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincare Ball}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28223-28232} }

MVBench: A Comprehensive Multi-modal Video Understanding Benchmark
Kunchang Li,
Yali Wang,
Yinan He,
Yizhuo Li,
Yi Wang,
Yi Liu,
Zun Wang,
Jilan Xu,
Guo Chen,
Ping Luo,
Limin Wang,
Yu Qiao
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Kunchang and Wang, Yali and He, Yinan and Li, Yizhuo and Wang, Yi and Liu, Yi and Wang, Zun and Xu, Jilan and Chen, Guo and Luo, Ping and Wang, Limin and Qiao, Yu}, title = {MVBench: A Comprehensive Multi-modal Video Understanding Benchmark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22195-22206} }

An Aggregation-Free Federated Learning for Tackling Data Heterogeneity
Yuan Wang,
Huazhu Fu,
Renuga Kanagavelu,
Qingsong Wei,
Yong Liu,
Rick Siow Mong Goh
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Yuan and Fu, Huazhu and Kanagavelu, Renuga and Wei, Qingsong and Liu, Yong and Goh, Rick Siow Mong}, title = {An Aggregation-Free Federated Learning for Tackling Data Heterogeneity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26233-26242} }

Hierarchical Intra-modal Correlation Learning for Label-free 3D Semantic Segmentation
Xin Kang,
Lei Chu,
Jiahao Li,
Xuejin Chen,
Yan Lu
[pdf] [supp]
[bibtex]
@InProceedings{Kang_2024_CVPR, author = {Kang, Xin and Chu, Lei and Li, Jiahao and Chen, Xuejin and Lu, Yan}, title = {Hierarchical Intra-modal Correlation Learning for Label-free 3D Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28244-28253} }

DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction
Junwen Xiong,
Peng Zhang,
Tao You,
Chuanyue Li,
Wei Huang,
Yufei Zha
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiong_2024_CVPR, author = {Xiong, Junwen and Zhang, Peng and You, Tao and Li, Chuanyue and Huang, Wei and Zha, Yufei}, title = {DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27273-27283} }

Revisiting Single Image Reflection Removal In the Wild
Yurui Zhu,
Xueyang Fu,
Peng-Tao Jiang,
Hao Zhang,
Qibin Sun,
Jinwei Chen,
Zheng-Jun Zha,
Bo Li
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2024_CVPR, author = {Zhu, Yurui and Fu, Xueyang and Jiang, Peng-Tao and Zhang, Hao and Sun, Qibin and Chen, Jinwei and Zha, Zheng-Jun and Li, Bo}, title = {Revisiting Single Image Reflection Removal In the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25468-25478} }

SinSR: Diffusion-Based Image Super-Resolution in a Single Step
Yufei Wang,
Wenhan Yang,
Xinyuan Chen,
Yaohui Wang,
Lanqing Guo,
Lap-Pui Chau,
Ziwei Liu,
Yu Qiao,
Alex C. Kot,
Bihan Wen
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Yufei and Yang, Wenhan and Chen, Xinyuan and Wang, Yaohui and Guo, Lanqing and Chau, Lap-Pui and Liu, Ziwei and Qiao, Yu and Kot, Alex C. and Wen, Bihan}, title = {SinSR: Diffusion-Based Image Super-Resolution in a Single Step}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25796-25805} }

Systematic Comparison of Semi-supervised and Self-supervised Learning for Medical Image Classification
Zhe Huang,
Ruijie Jiang,
Shuchin Aeron,
Michael C. Hughes
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2024_CVPR, author = {Huang, Zhe and Jiang, Ruijie and Aeron, Shuchin and Hughes, Michael C.}, title = {Systematic Comparison of Semi-supervised and Self-supervised Learning for Medical Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22282-22293} }

MSU-4S - The Michigan State University Four Seasons Dataset
Daniel Kent,
Mohammed Alyaqoub,
Xiaohu Lu,
Hamed Khatounabadi,
Kookjin Sung,
Cole Scheller,
Alexander Dalat,
Asma bin Thabit,
Roberto Whitley,
Hayder Radha
[pdf]
[bibtex]
@InProceedings{Kent_2024_CVPR, author = {Kent, Daniel and Alyaqoub, Mohammed and Lu, Xiaohu and Khatounabadi, Hamed and Sung, Kookjin and Scheller, Cole and Dalat, Alexander and bin Thabit, Asma and Whitley, Roberto and Radha, Hayder}, title = {MSU-4S - The Michigan State University Four Seasons Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22658-22667} }

Improving Plasticity in Online Continual Learning via Collaborative Learning
Maorong Wang,
Nicolas Michel,
Ling Xiao,
Toshihiko Yamasaki
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Maorong and Michel, Nicolas and Xiao, Ling and Yamasaki, Toshihiko}, title = {Improving Plasticity in Online Continual Learning via Collaborative Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23460-23469} }

Spectral and Polarization Vision: Spectro-polarimetric Real-world Dataset
Yujin Jeon,
Eunsue Choi,
Youngchan Kim,
Yunseong Moon,
Khalid Omer,
Felix Heide,
Seung-Hwan Baek
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jeon_2024_CVPR, author = {Jeon, Yujin and Choi, Eunsue and Kim, Youngchan and Moon, Yunseong and Omer, Khalid and Heide, Felix and Baek, Seung-Hwan}, title = {Spectral and Polarization Vision: Spectro-polarimetric Real-world Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22098-22108} }

Transfer CLIP for Generalizable Image Denoising
Jun Cheng,
Dong Liang,
Shan Tan
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2024_CVPR, author = {Cheng, Jun and Liang, Dong and Tan, Shan}, title = {Transfer CLIP for Generalizable Image Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25974-25984} }

Revisiting Adversarial Training at Scale
Zeyu Wang,
Xianhang Li,
Hongru Zhu,
Cihang Xie
[pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Zeyu and Li, Xianhang and Zhu, Hongru and Xie, Cihang}, title = {Revisiting Adversarial Training at Scale}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24675-24685} }

Towards Fairness-Aware Adversarial Learning
Yanghao Zhang,
Tianle Zhang,
Ronghui Mu,
Xiaowei Huang,
Wenjie Ruan
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Yanghao and Zhang, Tianle and Mu, Ronghui and Huang, Xiaowei and Ruan, Wenjie}, title = {Towards Fairness-Aware Adversarial Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24746-24755} }

MirageRoom: 3D Scene Segmentation with 2D Pre-trained Models by Mirage Projection
Haowen Sun,
Yueqi Duan,
Juncheng Yan,
Yifan Liu,
Jiwen Lu
[pdf] [supp]
[bibtex]
@InProceedings{Sun_2024_CVPR, author = {Sun, Haowen and Duan, Yueqi and Yan, Juncheng and Liu, Yifan and Lu, Jiwen}, title = {MirageRoom: 3D Scene Segmentation with 2D Pre-trained Models by Mirage Projection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20237-20246} }

In2SET: Intra-Inter Similarity Exploiting Transformer for Dual-Camera Compressive Hyperspectral Imaging
Xin Wang,
Lizhi Wang,
Xiangtian Ma,
Maoqing Zhang,
Lin Zhu,
Hua Huang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Xin and Wang, Lizhi and Ma, Xiangtian and Zhang, Maoqing and Zhu, Lin and Huang, Hua}, title = {In2SET: Intra-Inter Similarity Exploiting Transformer for Dual-Camera Compressive Hyperspectral Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24881-24891} }

Look-Up Table Compression for Efficient Image Restoration
Yinglong Li,
Jiacheng Li,
Zhiwei Xiong
[pdf] [supp]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Yinglong and Li, Jiacheng and Xiong, Zhiwei}, title = {Look-Up Table Compression for Efficient Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26016-26025} }

TextNeRF: A Novel Scene-Text Image Synthesis Method based on Neural Radiance Fields
Jialei Cui,
Jianwei Du,
Wenzhuo Liu,
Zhouhui Lian
[pdf] [supp]
[bibtex]
@InProceedings{Cui_2024_CVPR, author = {Cui, Jialei and Du, Jianwei and Liu, Wenzhuo and Lian, Zhouhui}, title = {TextNeRF: A Novel Scene-Text Image Synthesis Method based on Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22272-22281} }

Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-Training via Differentiable Rendering of Line Segments
Yusuke Takimoto,
Hikari Takehara,
Hiroyuki Sato,
Zihao Zhu,
Bo Zheng
[pdf] [supp]
[bibtex]
@InProceedings{Takimoto_2024_CVPR, author = {Takimoto, Yusuke and Takehara, Hikari and Sato, Hiroyuki and Zhu, Zihao and Zheng, Bo}, title = {Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-Training via Differentiable Rendering of Line Segments}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20601-20611} }

DiVa-360: The Dynamic Visual Dataset for Immersive Neural Fields
Cheng-You Lu,
Peisen Zhou,
Angela Xing,
Chandradeep Pokhariya,
Arnab Dey,
Ishaan Nikhil Shah,
Rugved Mavidipalli,
Dylan Hu,
Andrew I. Comport,
Kefan Chen,
Srinath Sridhar
[pdf] [supp]
[bibtex]
@InProceedings{Lu_2024_CVPR, author = {Lu, Cheng-You and Zhou, Peisen and Xing, Angela and Pokhariya, Chandradeep and Dey, Arnab and Shah, Ishaan Nikhil and Mavidipalli, Rugved and Hu, Dylan and Comport, Andrew I. and Chen, Kefan and Sridhar, Srinath}, title = {DiVa-360: The Dynamic Visual Dataset for Immersive Neural Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22466-22476} }

FSC: Few-point Shape Completion
Xianzu Wu,
Xianfeng Wu,
Tianyu Luan,
Yajing Bai,
Zhongyuan Lai,
Junsong Yuan
[pdf] [arXiv]
[bibtex]
@InProceedings{Wu_2024_CVPR, author = {Wu, Xianzu and Wu, Xianfeng and Luan, Tianyu and Bai, Yajing and Lai, Zhongyuan and Yuan, Junsong}, title = {FSC: Few-point Shape Completion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26077-26087} }

T-VSL: Text-Guided Visual Sound Source Localization in Mixtures
Tanvir Mahmud,
Yapeng Tian,
Diana Marculescu
[pdf] [supp]
[bibtex]
@InProceedings{Mahmud_2024_CVPR, author = {Mahmud, Tanvir and Tian, Yapeng and Marculescu, Diana}, title = {T-VSL: Text-Guided Visual Sound Source Localization in Mixtures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26742-26751} }

VCoder: Versatile Vision Encoders for Multimodal Large Language Models
Jitesh Jain,
Jianwei Yang,
Humphrey Shi
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jain_2024_CVPR, author = {Jain, Jitesh and Yang, Jianwei and Shi, Humphrey}, title = {VCoder: Versatile Vision Encoders for Multimodal Large Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27992-28002} }

Event-based Visible and Infrared Fusion via Multi-task Collaboration
Mengyue Geng,
Lin Zhu,
Lizhi Wang,
Wei Zhang,
Ruiqin Xiong,
Yonghong Tian
[pdf] [supp]
[bibtex]
@InProceedings{Geng_2024_CVPR, author = {Geng, Mengyue and Zhu, Lin and Wang, Lizhi and Zhang, Wei and Xiong, Ruiqin and Tian, Yonghong}, title = {Event-based Visible and Infrared Fusion via Multi-task Collaboration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26929-26939} }

RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding
Jihan Yang,
Runyu Ding,
Weipeng Deng,
Zhe Wang,
Xiaojuan Qi
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2024_CVPR, author = {Yang, Jihan and Ding, Runyu and Deng, Weipeng and Wang, Zhe and Qi, Xiaojuan}, title = {RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19823-19832} }

Three Pillars Improving Vision Foundation Model Distillation for Lidar
Gilles Puy,
Spyros Gidaris,
Alexandre Boulch,
Oriane Siméoni,
Corentin Sautier,
Patrick Pérez,
Andrei Bursuc,
Renaud Marlet
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Puy_2024_CVPR, author = {Puy, Gilles and Gidaris, Spyros and Boulch, Alexandre and Sim\'eoni, Oriane and Sautier, Corentin and P\'erez, Patrick and Bursuc, Andrei and Marlet, Renaud}, title = {Three Pillars Improving Vision Foundation Model Distillation for Lidar}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21519-21529} }

ShapeWalk: Compositional Shape Editing Through Language-Guided Chains
Habib Slim,
Mohamed Elhoseiny
[pdf] [supp]
[bibtex]
@InProceedings{Slim_2024_CVPR, author = {Slim, Habib and Elhoseiny, Mohamed}, title = {ShapeWalk: Compositional Shape Editing Through Language-Guided Chains}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22574-22583} }

MESA: Matching Everything by Segmenting Anything
Yesheng Zhang,
Xu Zhao
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Yesheng and Zhao, Xu}, title = {MESA: Matching Everything by Segmenting Anything}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20217-20226} }

Learning Degradation-Independent Representations for Camera ISP Pipelines
Yanhui Guo,
Fangzhou Luo,
Xiaolin Wu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2024_CVPR, author = {Guo, Yanhui and Luo, Fangzhou and Wu, Xiaolin}, title = {Learning Degradation-Independent Representations for Camera ISP Pipelines}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25774-25783} }

OmniGlue: Generalizable Feature Matching with Foundation Model Guidance
Hanwen Jiang,
Arjun Karpur,
Bingyi Cao,
Qixing Huang,
André Araujo
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2024_CVPR, author = {Jiang, Hanwen and Karpur, Arjun and Cao, Bingyi and Huang, Qixing and Araujo, Andr\'e}, title = {OmniGlue: Generalizable Feature Matching with Foundation Model Guidance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19865-19875} }

OmniSDF: Scene Reconstruction using Omnidirectional Signed Distance Functions and Adaptive Binoctrees
Hakyeong Kim,
Andreas Meuleman,
Hyeonjoong Jang,
James Tompkin,
Min H. Kim
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_CVPR, author = {Kim, Hakyeong and Meuleman, Andreas and Jang, Hyeonjoong and Tompkin, James and Kim, Min H.}, title = {OmniSDF: Scene Reconstruction using Omnidirectional Signed Distance Functions and Adaptive Binoctrees}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20227-20236} }

Generating Content for HDR Deghosting from Frequency View
Tao Hu,
Qingsen Yan,
Yuankai Qi,
Yanning Zhang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hu_2024_CVPR, author = {Hu, Tao and Yan, Qingsen and Qi, Yuankai and Zhang, Yanning}, title = {Generating Content for HDR Deghosting from Frequency View}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25732-25741} }

LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes
Yanwen Guo,
Yuanqi Li,
Dayong Ren,
Xiaohong Zhang,
Jiawei Li,
Liang Pu,
Changfeng Ma,
Xiaoyu Zhan,
Jie Guo,
Mingqiang Wei,
Yan Zhang,
Piaopiao Yu,
Shuangyu Yang,
Donghao Ji,
Huisheng Ye,
Hao Sun,
Yansong Liu,
Yinuo Chen,
Jiaqi Zhu,
Hongyu Liu
[pdf] [supp]
[bibtex]
@InProceedings{Guo_2024_CVPR, author = {Guo, Yanwen and Li, Yuanqi and Ren, Dayong and Zhang, Xiaohong and Li, Jiawei and Pu, Liang and Ma, Changfeng and Zhan, Xiaoyu and Guo, Jie and Wei, Mingqiang and Zhang, Yan and Yu, Piaopiao and Yang, Shuangyu and Ji, Donghao and Ye, Huisheng and Sun, Hao and Liu, Yansong and Chen, Yinuo and Zhu, Jiaqi and Liu, Hongyu}, title = {LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21989-21999} }

Rich Human Feedback for Text-to-Image Generation
Youwei Liang,
Junfeng He,
Gang Li,
Peizhao Li,
Arseniy Klimovskiy,
Nicholas Carolan,
Jiao Sun,
Jordi Pont-Tuset,
Sarah Young,
Feng Yang,
Junjie Ke,
Krishnamurthy Dj Dvijotham,
Katherine M. Collins,
Yiwen Luo,
Yang Li,
Kai J Kohlhoff,
Deepak Ramachandran,
Vidhya Navalpakkam
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liang_2024_CVPR, author = {Liang, Youwei and He, Junfeng and Li, Gang and Li, Peizhao and Klimovskiy, Arseniy and Carolan, Nicholas and Sun, Jiao and Pont-Tuset, Jordi and Young, Sarah and Yang, Feng and Ke, Junjie and Dvijotham, Krishnamurthy Dj and Collins, Katherine M. and Luo, Yiwen and Li, Yang and Kohlhoff, Kai J and Ramachandran, Deepak and Navalpakkam, Vidhya}, title = {Rich Human Feedback for Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19401-19411} }

Map-Relative Pose Regression for Visual Re-Localization
Shuai Chen,
Tommaso Cavallari,
Victor Adrian Prisacariu,
Eric Brachmann
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Shuai and Cavallari, Tommaso and Prisacariu, Victor Adrian and Brachmann, Eric}, title = {Map-Relative Pose Regression for Visual Re-Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20665-20674} }

Implicit Event-RGBD Neural SLAM
Delin Qu,
Chi Yan,
Dong Wang,
Jie Yin,
Qizhi Chen,
Dan Xu,
Yiting Zhang,
Bin Zhao,
Xuelong Li
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qu_2024_CVPR, author = {Qu, Delin and Yan, Chi and Wang, Dong and Yin, Jie and Chen, Qizhi and Xu, Dan and Zhang, Yiting and Zhao, Bin and Li, Xuelong}, title = {Implicit Event-RGBD Neural SLAM}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19584-19594} }

Domain-Specific Block Selection and Paired-View Pseudo-Labeling for Online Test-Time Adaptation
Yeonguk Yu,
Sungho Shin,
Seunghyeok Back,
Mihwan Ko,
Sangjun Noh,
Kyoobin Lee
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2024_CVPR, author = {Yu, Yeonguk and Shin, Sungho and Back, Seunghyeok and Ko, Mihwan and Noh, Sangjun and Lee, Kyoobin}, title = {Domain-Specific Block Selection and Paired-View Pseudo-Labeling for Online Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22723-22732} }

Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery
Yuqi Zhang,
Guanying Chen,
Jiaxing Chen,
Shuguang Cui
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Yuqi and Chen, Guanying and Chen, Jiaxing and Cui, Shuguang}, title = {Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21092-21103} }

Learning with Structural Labels for Learning with Noisy Labels
Noo-ri Kim,
Jin-Seop Lee,
Jee-Hyong Lee
[pdf] [supp]
[bibtex]
@InProceedings{Kim_2024_CVPR, author = {Kim, Noo-ri and Lee, Jin-Seop and Lee, Jee-Hyong}, title = {Learning with Structural Labels for Learning with Noisy Labels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27610-27620} }

DeMatch: Deep Decomposition of Motion Field for Two-View Correspondence Learning
Shihua Zhang,
Zizhuo Li,
Yuan Gao,
Jiayi Ma
[pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Shihua and Li, Zizhuo and Gao, Yuan and Ma, Jiayi}, title = {DeMatch: Deep Decomposition of Motion Field for Two-View Correspondence Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20278-20287} }

Sherpa3D: Boosting High-Fidelity Text-to-3D Generation via Coarse 3D Prior
Fangfu Liu,
Diankun Wu,
Yi Wei,
Yongming Rao,
Yueqi Duan
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Fangfu and Wu, Diankun and Wei, Yi and Rao, Yongming and Duan, Yueqi}, title = {Sherpa3D: Boosting High-Fidelity Text-to-3D Generation via Coarse 3D Prior}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20763-20774} }

A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals
Jiangnan Tang,
Jingya Wang,
Kaiyang Ji,
Lan Xu,
Jingyi Yu,
Ye Shi
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tang_2024_CVPR, author = {Tang, Jiangnan and Wang, Jingya and Ji, Kaiyang and Xu, Lan and Yu, Jingyi and Shi, Ye}, title = {A Unified Diffusion Framework for Scene-aware Human Motion Estimation from Sparse Signals}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21251-21262} }

Single Domain Generalization for Crowd Counting
Zhuoxuan Peng,
S.-H. Gary Chan
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Peng_2024_CVPR, author = {Peng, Zhuoxuan and Chan, S.-H. Gary}, title = {Single Domain Generalization for Crowd Counting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28025-28034} }

Task-Aware Encoder Control for Deep Video Compression
Xingtong Ge,
Jixiang Luo,
Xinjie Zhang,
Tongda Xu,
Guo Lu,
Dailan He,
Jing Geng,
Yan Wang,
Jun Zhang,
Hongwei Qin
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ge_2024_CVPR, author = {Ge, Xingtong and Luo, Jixiang and Zhang, Xinjie and Xu, Tongda and Lu, Guo and He, Dailan and Geng, Jing and Wang, Yan and Zhang, Jun and Qin, Hongwei}, title = {Task-Aware Encoder Control for Deep Video Compression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26036-26045} }

Long-Tail Class Incremental Learning via Independent Sub-prototype Construction
Xi Wang,
Xu Yang,
Jie Yin,
Kun Wei,
Cheng Deng
[pdf] [supp]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Xi and Yang, Xu and Yin, Jie and Wei, Kun and Deng, Cheng}, title = {Long-Tail Class Incremental Learning via Independent Sub-prototype Construction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28598-28607} }

Learning with Unreliability: Fast Few-shot Voxel Radiance Fields with Relative Geometric Consistency
Yingjie Xu,
Bangzhen Liu,
Hao Tang,
Bailin Deng,
Shengfeng He
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2024_CVPR, author = {Xu, Yingjie and Liu, Bangzhen and Tang, Hao and Deng, Bailin and He, Shengfeng}, title = {Learning with Unreliability: Fast Few-shot Voxel Radiance Fields with Relative Geometric Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20342-20351} }

Towards Understanding and Improving Adversarial Robustness of Vision Transformers
Samyak Jain,
Tanima Dutta
[pdf] [supp]
[bibtex]
@InProceedings{Jain_2024_CVPR, author = {Jain, Samyak and Dutta, Tanima}, title = {Towards Understanding and Improving Adversarial Robustness of Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24736-24745} }

S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes
Xingyi Li,
Zhiguo Cao,
Yizheng Wu,
Kewei Wang,
Ke Xian,
Zhe Wang,
Guosheng Lin
[pdf] [supp]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Xingyi and Cao, Zhiguo and Wu, Yizheng and Wang, Kewei and Xian, Ke and Wang, Zhe and Lin, Guosheng}, title = {S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20102-20112} }

What How and When Should Object Detectors Update in Continually Changing Test Domains?
Jayeon Yoo,
Dongkwan Lee,
Inseop Chung,
Donghyun Kim,
Nojun Kwak
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yoo_2024_CVPR, author = {Yoo, Jayeon and Lee, Dongkwan and Chung, Inseop and Kim, Donghyun and Kwak, Nojun}, title = {What How and When Should Object Detectors Update in Continually Changing Test Domains?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23354-23363} }

Bayesian Exploration of Pre-trained Models for Low-shot Image Classification
Yibo Miao,
Yu Lei,
Feng Zhou,
Zhijie Deng
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Miao_2024_CVPR, author = {Miao, Yibo and Lei, Yu and Zhou, Feng and Deng, Zhijie}, title = {Bayesian Exploration of Pre-trained Models for Low-shot Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23849-23859} }

RoMa: Robust Dense Feature Matching
Johan Edstedt,
Qiyu Sun,
Georg Bökman,
Mårten Wadenbäck,
Michael Felsberg
[pdf] [supp]
[bibtex]
@InProceedings{Edstedt_2024_CVPR, author = {Edstedt, Johan and Sun, Qiyu and B\"okman, Georg and Wadenb\"ack, M\r{a}rten and Felsberg, Michael}, title = {RoMa: Robust Dense Feature Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19790-19800} }

Insights from the Use of Previously Unseen Neural Architecture Search Datasets
Rob Geada,
David Towers,
Matthew Forshaw,
Amir Atapour-Abarghouei,
A. Stephen McGough
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Geada_2024_CVPR, author = {Geada, Rob and Towers, David and Forshaw, Matthew and Atapour-Abarghouei, Amir and McGough, A. Stephen}, title = {Insights from the Use of Previously Unseen Neural Architecture Search Datasets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22541-22550} }

Adversarially Robust Few-shot Learning via Parameter Co-distillation of Similarity and Class Concept Learners
Junhao Dong,
Piotr Koniusz,
Junxi Chen,
Xiaohua Xie,
Yew-Soon Ong
[pdf] [supp]
[bibtex]
@InProceedings{Dong_2024_CVPR, author = {Dong, Junhao and Koniusz, Piotr and Chen, Junxi and Xie, Xiaohua and Ong, Yew-Soon}, title = {Adversarially Robust Few-shot Learning via Parameter Co-distillation of Similarity and Class Concept Learners}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28535-28544} }

APISR: Anime Production Inspired Real-World Anime Super-Resolution
Boyang Wang,
Fengyu Yang,
Xihang Yu,
Chao Zhang,
Hanbin Zhao
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Boyang and Yang, Fengyu and Yu, Xihang and Zhang, Chao and Zhao, Hanbin}, title = {APISR: Anime Production Inspired Real-World Anime Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25574-25584} }

MVCPS-NeuS: Multi-view Constrained Photometric Stereo for Neural Surface Reconstruction
Hiroaki Santo,
Fumio Okura,
Yasuyuki Matsushita
[pdf] [supp]
[bibtex]
@InProceedings{Santo_2024_CVPR, author = {Santo, Hiroaki and Okura, Fumio and Matsushita, Yasuyuki}, title = {MVCPS-NeuS: Multi-view Constrained Photometric Stereo for Neural Surface Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20475-20484} }

ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding
Le Xue,
Ning Yu,
Shu Zhang,
Artemis Panagopoulou,
Junnan Li,
Roberto Martín-Martín,
Jiajun Wu,
Caiming Xiong,
Ran Xu,
Juan Carlos Niebles,
Silvio Savarese
[pdf] [supp]
[bibtex]
@InProceedings{Xue_2024_CVPR, author = {Xue, Le and Yu, Ning and Zhang, Shu and Panagopoulou, Artemis and Li, Junnan and Mart{\'\i}n-Mart{\'\i}n, Roberto and Wu, Jiajun and Xiong, Caiming and Xu, Ran and Niebles, Juan Carlos and Savarese, Silvio}, title = {ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27091-27101} }

WaveMo: Learning Wavefront Modulations to See Through Scattering
Mingyang Xie,
Haiyun Guo,
Brandon Y. Feng,
Lingbo Jin,
Ashok Veeraraghavan,
Christopher A. Metzler
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xie_2024_CVPR, author = {Xie, Mingyang and Guo, Haiyun and Feng, Brandon Y. and Jin, Lingbo and Veeraraghavan, Ashok and Metzler, Christopher A.}, title = {WaveMo: Learning Wavefront Modulations to See Through Scattering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25276-25285} }

Integrating Efficient Optimal Transport and Functional Maps For Unsupervised Shape Correspondence Learning
Tung Le,
Khai Nguyen,
Shanlin Sun,
Nhat Ho,
Xiaohui Xie
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Le_2024_CVPR, author = {Le, Tung and Nguyen, Khai and Sun, Shanlin and Ho, Nhat and Xie, Xiaohui}, title = {Integrating Efficient Optimal Transport and Functional Maps For Unsupervised Shape Correspondence Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23188-23198} }

ODCR: Orthogonal Decoupling Contrastive Regularization for Unpaired Image Dehazing
Zhongze Wang,
Haitao Zhao,
Jingchao Peng,
Lujian Yao,
Kaijie Zhao
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Zhongze and Zhao, Haitao and Peng, Jingchao and Yao, Lujian and Zhao, Kaijie}, title = {ODCR: Orthogonal Decoupling Contrastive Regularization for Unpaired Image Dehazing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25479-25489} }

OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning
Haiyang Ying,
Yixuan Yin,
Jinzhi Zhang,
Fan Wang,
Tao Yu,
Ruqi Huang,
Lu Fang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ying_2024_CVPR, author = {Ying, Haiyang and Yin, Yixuan and Zhang, Jinzhi and Wang, Fan and Yu, Tao and Huang, Ruqi and Fang, Lu}, title = {OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20612-20622} }

Simple Semantic-Aided Few-Shot Learning
Hai Zhang,
Junzhe Xu,
Shanlin Jiang,
Zhenan He
[pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Hai and Xu, Junzhe and Jiang, Shanlin and He, Zhenan}, title = {Simple Semantic-Aided Few-Shot Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28588-28597} }

Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification
Chao Yi,
Lu Ren,
De-Chuan Zhan,
Han-Jia Ye
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yi_2024_CVPR, author = {Yi, Chao and Ren, Lu and Zhan, De-Chuan and Ye, Han-Jia}, title = {Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27402-27411} }

Revisiting Adversarial Training Under Long-Tailed Distributions
Xinli Yue,
Ningping Mou,
Qian Wang,
Lingchen Zhao
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yue_2024_CVPR, author = {Yue, Xinli and Mou, Ningping and Wang, Qian and Zhao, Lingchen}, title = {Revisiting Adversarial Training Under Long-Tailed Distributions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24492-24501} }

Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models
Zhang Li,
Biao Yang,
Qiang Liu,
Zhiyin Ma,
Shuo Zhang,
Jingxu Yang,
Yabo Sun,
Yuliang Liu,
Xiang Bai
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Zhang and Yang, Biao and Liu, Qiang and Ma, Zhiyin and Zhang, Shuo and Yang, Jingxu and Sun, Yabo and Liu, Yuliang and Bai, Xiang}, title = {Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26763-26773} }

Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation
Fahimeh Hosseini Noohdani,
Parsa Hosseini,
Aryan Yazdan Parast,
Hamidreza Yaghoubi Araghi,
Mahdieh Soleymani Baghshah
[pdf] [supp]
[bibtex]
@InProceedings{Noohdani_2024_CVPR, author = {Noohdani, Fahimeh Hosseini and Hosseini, Parsa and Parast, Aryan Yazdan and Araghi, Hamidreza Yaghoubi and Baghshah, Mahdieh Soleymani}, title = {Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27662-27671} }

BEM: Balanced and Entropy-based Mix for Long-Tailed Semi-Supervised Learning
Hongwei Zheng,
Linyuan Zhou,
Han Li,
Jinming Su,
Xiaoming Wei,
Xiaoming Xu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2024_CVPR, author = {Zheng, Hongwei and Zhou, Linyuan and Li, Han and Su, Jinming and Wei, Xiaoming and Xu, Xiaoming}, title = {BEM: Balanced and Entropy-based Mix for Long-Tailed Semi-Supervised Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22893-22903} }

HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting
Hongyu Zhou,
Jiahao Shao,
Lu Xu,
Dongfeng Bai,
Weichao Qiu,
Bingbing Liu,
Yue Wang,
Andreas Geiger,
Yiyi Liao
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2024_CVPR, author = {Zhou, Hongyu and Shao, Jiahao and Xu, Lu and Bai, Dongfeng and Qiu, Weichao and Liu, Bingbing and Wang, Yue and Geiger, Andreas and Liao, Yiyi}, title = {HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21336-21345} }

GeoAuxNet: Towards Universal 3D Representation Learning for Multi-sensor Point Clouds
Shengjun Zhang,
Xin Fei,
Yueqi Duan
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Shengjun and Fei, Xin and Duan, Yueqi}, title = {GeoAuxNet: Towards Universal 3D Representation Learning for Multi-sensor Point Clouds}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20019-20028} }

Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling
Shentong Mo,
Pedro Morgado
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mo_2024_CVPR, author = {Mo, Shentong and Morgado, Pedro}, title = {Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27186-27196} }

RepKPU: Point Cloud Upsampling with Kernel Point Representation and Deformation
Yi Rong,
Haoran Zhou,
Kang Xia,
Cheng Mei,
Jiahao Wang,
Tong Lu
[pdf] [supp]
[bibtex]
@InProceedings{Rong_2024_CVPR, author = {Rong, Yi and Zhou, Haoran and Xia, Kang and Mei, Cheng and Wang, Jiahao and Lu, Tong}, title = {RepKPU: Point Cloud Upsampling with Kernel Point Representation and Deformation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21050-21060} }

ConCon-Chi: Concept-Context Chimera Benchmark for Personalized Vision-Language Tasks
Andrea Rosasco,
Stefano Berti,
Giulia Pasquale,
Damiano Malafronte,
Shogo Sato,
Hiroyuki Segawa,
Tetsugo Inada,
Lorenzo Natale
[pdf] [supp]
[bibtex]
@InProceedings{Rosasco_2024_CVPR, author = {Rosasco, Andrea and Berti, Stefano and Pasquale, Giulia and Malafronte, Damiano and Sato, Shogo and Segawa, Hiroyuki and Inada, Tetsugo and Natale, Lorenzo}, title = {ConCon-Chi: Concept-Context Chimera Benchmark for Personalized Vision-Language Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22239-22248} }

MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers
Yawar Siddiqui,
Antonio Alliegro,
Alexey Artemov,
Tatiana Tommasi,
Daniele Sirigatti,
Vladislav Rosov,
Angela Dai,
Matthias Nießner
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Siddiqui_2024_CVPR, author = {Siddiqui, Yawar and Alliegro, Antonio and Artemov, Alexey and Tommasi, Tatiana and Sirigatti, Daniele and Rosov, Vladislav and Dai, Angela and Nie{\ss}ner, Matthias}, title = {MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19615-19625} }

Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance
Tomer Garber,
Tom Tirer
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Garber_2024_CVPR, author = {Garber, Tomer and Tirer, Tom}, title = {Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25245-25254} }

MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark
Sanghyun Woo,
Kwanyong Park,
Inkyu Shin,
Myungchul Kim,
In So Kweon
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Woo_2024_CVPR, author = {Woo, Sanghyun and Park, Kwanyong and Shin, Inkyu and Kim, Myungchul and Kweon, In So}, title = {MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22335-22346} }

DAP: A Dynamic Adversarial Patch for Evading Person Detectors
Amira Guesmi,
Ruitian Ding,
Muhammad Abdullah Hanif,
Ihsen Alouani,
Muhammad Shafique
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guesmi_2024_CVPR, author = {Guesmi, Amira and Ding, Ruitian and Hanif, Muhammad Abdullah and Alouani, Ihsen and Shafique, Muhammad}, title = {DAP: A Dynamic Adversarial Patch for Evading Person Detectors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24595-24604} }

Learned Lossless Image Compression based on Bit Plane Slicing
Zhe Zhang,
Huairui Wang,
Zhenzhong Chen,
Shan Liu
[pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Zhe and Wang, Huairui and Chen, Zhenzhong and Liu, Shan}, title = {Learned Lossless Image Compression based on Bit Plane Slicing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27579-27588} }

Flexible Depth Completion for Sparse and Varying Point Densities
Jinhyung Park,
Yu-Jhe Li,
Kris Kitani
[pdf] [supp]
[bibtex]
@InProceedings{Park_2024_CVPR, author = {Park, Jinhyung and Li, Yu-Jhe and Kitani, Kris}, title = {Flexible Depth Completion for Sparse and Varying Point Densities}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21540-21550} }

Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now
Ayush Sarkar,
Hanlin Mai,
Amitabh Mahapatra,
Svetlana Lazebnik,
D.A. Forsyth,
Anand Bhattad
[pdf] [supp]
[bibtex]
@InProceedings{Sarkar_2024_CVPR, author = {Sarkar, Ayush and Mai, Hanlin and Mahapatra, Amitabh and Lazebnik, Svetlana and Forsyth, D.A. and Bhattad, Anand}, title = {Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28140-28149} }

GEARS: Local Geometry-aware Hand-object Interaction Synthesis
Keyang Zhou,
Bharat Lal Bhatnagar,
Jan Eric Lenssen,
Gerard Pons-Moll
[pdf] [arXiv]
[bibtex]
@InProceedings{Zhou_2024_CVPR, author = {Zhou, Keyang and Bhatnagar, Bharat Lal and Lenssen, Jan Eric and Pons-Moll, Gerard}, title = {GEARS: Local Geometry-aware Hand-object Interaction Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20634-20643} }

CodedEvents: Optimal Point-Spread-Function Engineering for 3D-Tracking with Event Cameras
Sachin Shah,
Matthew A. Chan,
Haoming Cai,
Jingxi Chen,
Sakshum Kulshrestha,
Chahat Deep Singh,
Yiannis Aloimonos,
Christopher A. Metzler
[pdf] [supp]
[bibtex]
@InProceedings{Shah_2024_CVPR, author = {Shah, Sachin and Chan, Matthew A. and Cai, Haoming and Chen, Jingxi and Kulshrestha, Sakshum and Singh, Chahat Deep and Aloimonos, Yiannis and Metzler, Christopher A.}, title = {CodedEvents: Optimal Point-Spread-Function Engineering for 3D-Tracking with Event Cameras}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25265-25275} }

Learning Discriminative Dynamics with Label Corruption for Noisy Label Detection
Suyeon Kim,
Dongha Lee,
SeongKu Kang,
Sukang Chae,
Sanghwan Jang,
Hwanjo Yu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_CVPR, author = {Kim, Suyeon and Lee, Dongha and Kang, SeongKu and Chae, Sukang and Jang, Sanghwan and Yu, Hwanjo}, title = {Learning Discriminative Dynamics with Label Corruption for Noisy Label Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22477-22487} }

DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning
Sikai Bai,
Jie Zhang,
Song Guo,
Shuaicheng Li,
Jingcai Guo,
Jun Hou,
Tao Han,
Xiaocheng Lu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bai_2024_CVPR, author = {Bai, Sikai and Zhang, Jie and Guo, Song and Li, Shuaicheng and Guo, Jingcai and Hou, Jun and Han, Tao and Lu, Xiaocheng}, title = {DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27284-27293} }

Adversarial Distillation Based on Slack Matching and Attribution Region Alignment
Shenglin Yin,
Zhen Xiao,
Mingxuan Song,
Jieyi Long
[pdf] [supp]
[bibtex]
@InProceedings{Yin_2024_CVPR, author = {Yin, Shenglin and Xiao, Zhen and Song, Mingxuan and Long, Jieyi}, title = {Adversarial Distillation Based on Slack Matching and Attribution Region Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24605-24614} }

Boosting Spike Camera Image Reconstruction from a Perspective of Dealing with Spike Fluctuations
Rui Zhao,
Ruiqin Xiong,
Jing Zhao,
Jian Zhang,
Xiaopeng Fan,
Zhaofei Yu,
Tiejun Huang
[pdf] [supp]
[bibtex]
@InProceedings{Zhao_2024_CVPR, author = {Zhao, Rui and Xiong, Ruiqin and Zhao, Jing and Zhang, Jian and Fan, Xiaopeng and Yu, Zhaofei and Huang, Tiejun}, title = {Boosting Spike Camera Image Reconstruction from a Perspective of Dealing with Spike Fluctuations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24955-24965} }

Text-guided Explorable Image Super-resolution
Kanchana Vaishnavi Gandikota,
Paramanand Chandramouli
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gandikota_2024_CVPR, author = {Gandikota, Kanchana Vaishnavi and Chandramouli, Paramanand}, title = {Text-guided Explorable Image Super-resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25900-25911} }

Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation
Haojie Zhang,
Yongyi Su,
Xun Xu,
Kui Jia
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Haojie and Su, Yongyi and Xu, Xun and Jia, Kui}, title = {Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23385-23395} }

Correspondence-Free Non-Rigid Point Set Registration Using Unsupervised Clustering Analysis
Mingyang Zhao,
Jingen Jiang,
Lei Ma,
Shiqing Xin,
Gaofeng Meng,
Dong-Ming Yan
[pdf] [supp]
[bibtex]
@InProceedings{Zhao_2024_CVPR, author = {Zhao, Mingyang and Jiang, Jingen and Ma, Lei and Xin, Shiqing and Meng, Gaofeng and Yan, Dong-Ming}, title = {Correspondence-Free Non-Rigid Point Set Registration Using Unsupervised Clustering Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21199-21208} }

BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP
Jiawang Bai,
Kuofeng Gao,
Shaobo Min,
Shu-Tao Xia,
Zhifeng Li,
Wei Liu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bai_2024_CVPR, author = {Bai, Jiawang and Gao, Kuofeng and Min, Shaobo and Xia, Shu-Tao and Li, Zhifeng and Liu, Wei}, title = {BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24239-24250} }

PixelRNN: In-pixel Recurrent Neural Networks for End-to-end-optimized Perception with Neural Sensors
Haley M. So,
Laurie Bose,
Piotr Dudek,
Gordon Wetzstein
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{So_2024_CVPR, author = {So, Haley M. and Bose, Laurie and Dudek, Piotr and Wetzstein, Gordon}, title = {PixelRNN: In-pixel Recurrent Neural Networks for End-to-end-optimized Perception with Neural Sensors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25233-25244} }

DUSt3R: Geometric 3D Vision Made Easy
Shuzhe Wang,
Vincent Leroy,
Yohann Cabon,
Boris Chidlovskii,
Jerome Revaud
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Shuzhe and Leroy, Vincent and Cabon, Yohann and Chidlovskii, Boris and Revaud, Jerome}, title = {DUSt3R: Geometric 3D Vision Made Easy}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20697-20709} }

Robust Distillation via Untargeted and Targeted Intermediate Adversarial Samples
Junhao Dong,
Piotr Koniusz,
Junxi Chen,
Z. Jane Wang,
Yew-Soon Ong
[pdf] [supp]
[bibtex]
@InProceedings{Dong_2024_CVPR, author = {Dong, Junhao and Koniusz, Piotr and Chen, Junxi and Wang, Z. Jane and Ong, Yew-Soon}, title = {Robust Distillation via Untargeted and Targeted Intermediate Adversarial Samples}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28432-28442} }

Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement
Zhuorong Li,
Daiwei Yu,
Lina Wei,
Canghong Jin,
Yun Zhang,
Sixian Chan
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Zhuorong and Yu, Daiwei and Wei, Lina and Jin, Canghong and Zhang, Yun and Chan, Sixian}, title = {Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24776-24785} }

Pose-Guided Self-Training with Two-Stage Clustering for Unsupervised Landmark Discovery
Siddharth Tourani,
Ahmed Alwheibi,
Arif Mahmood,
Muhammad Haris Khan
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tourani_2024_CVPR, author = {Tourani, Siddharth and Alwheibi, Ahmed and Mahmood, Arif and Khan, Muhammad Haris}, title = {Pose-Guided Self-Training with Two-Stage Clustering for Unsupervised Landmark Discovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23041-23051} }

Learning from Synthetic Human Group Activities
Che-Jui Chang,
Danrui Li,
Deep Patel,
Parth Goel,
Honglu Zhou,
Seonghyeon Moon,
Samuel S. Sohn,
Sejong Yoon,
Vladimir Pavlovic,
Mubbasir Kapadia
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chang_2024_CVPR, author = {Chang, Che-Jui and Li, Danrui and Patel, Deep and Goel, Parth and Zhou, Honglu and Moon, Seonghyeon and Sohn, Samuel S. and Yoon, Sejong and Pavlovic, Vladimir and Kapadia, Mubbasir}, title = {Learning from Synthetic Human Group Activities}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21922-21932} }

Text Grouping Adapter: Adapting Pre-trained Text Detector for Layout Analysis
Tianci Bi,
Xiaoyi Zhang,
Zhizheng Zhang,
Wenxuan Xie,
Cuiling Lan,
Yan Lu,
Nanning Zheng
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bi_2024_CVPR, author = {Bi, Tianci and Zhang, Xiaoyi and Zhang, Zhizheng and Xie, Wenxuan and Lan, Cuiling and Lu, Yan and Zheng, Nanning}, title = {Text Grouping Adapter: Adapting Pre-trained Text Detector for Layout Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28150-28159} }

THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Models
Prannay Kaul,
Zhizhong Li,
Hao Yang,
Yonatan Dukler,
Ashwin Swaminathan,
C. J. Taylor,
Stefano Soatto
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kaul_2024_CVPR, author = {Kaul, Prannay and Li, Zhizhong and Yang, Hao and Dukler, Yonatan and Swaminathan, Ashwin and Taylor, C. J. and Soatto, Stefano}, title = {THRONE: An Object-based Hallucination Benchmark for the Free-form Generations of Large Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27228-27238} }

LUWA Dataset: Learning Lithic Use-Wear Analysis on Microscopic Images
Jing Zhang,
Irving Fang,
Hao Wu,
Akshat Kaushik,
Alice Rodriguez,
Hanwen Zhao,
Juexiao Zhang,
Zhuo Zheng,
Radu Iovita,
Chen Feng
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Jing and Fang, Irving and Wu, Hao and Kaushik, Akshat and Rodriguez, Alice and Zhao, Hanwen and Zhang, Juexiao and Zheng, Zhuo and Iovita, Radu and Feng, Chen}, title = {LUWA Dataset: Learning Lithic Use-Wear Analysis on Microscopic Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22563-22573} }

The Audio-Visual Conversational Graph: From an Egocentric-Exocentric Perspective
Wenqi Jia,
Miao Liu,
Hao Jiang,
Ishwarya Ananthabhotla,
James M. Rehg,
Vamsi Krishna Ithapu,
Ruohan Gao
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jia_2024_CVPR, author = {Jia, Wenqi and Liu, Miao and Jiang, Hao and Ananthabhotla, Ishwarya and Rehg, James M. and Ithapu, Vamsi Krishna and Gao, Ruohan}, title = {The Audio-Visual Conversational Graph: From an Egocentric-Exocentric Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26396-26405} }

Byzantine-robust Decentralized Federated Learning via Dual-domain Clustering and Trust Bootstrapping
Peng Sun,
Xinyang Liu,
Zhibo Wang,
Bo Liu
[pdf] [supp]
[bibtex]
@InProceedings{Sun_2024_CVPR, author = {Sun, Peng and Liu, Xinyang and Wang, Zhibo and Liu, Bo}, title = {Byzantine-robust Decentralized Federated Learning via Dual-domain Clustering and Trust Bootstrapping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24756-24765} }

No More Ambiguity in 360deg Room Layout via Bi-Layout Estimation
Yu-Ju Tsai,
Jin-Cheng Jhang,
Jingjing Zheng,
Wei Wang,
Albert Y. C. Chen,
Min Sun,
Cheng-Hao Kuo,
Ming-Hsuan Yang
[pdf] [supp]
[bibtex]
@InProceedings{Tsai_2024_CVPR, author = {Tsai, Yu-Ju and Jhang, Jin-Cheng and Zheng, Jingjing and Wang, Wei and Chen, Albert Y. C. and Sun, Min and Kuo, Cheng-Hao and Yang, Ming-Hsuan}, title = {No More Ambiguity in 360deg Room Layout via Bi-Layout Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28056-28065} }

A Noisy Elephant in the Room: Is Your Out-of-Distribution Detector Robust to Label Noise?
Galadrielle Humblot-Renaux,
Sergio Escalera,
Thomas B. Moeslund
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Humblot-Renaux_2024_CVPR, author = {Humblot-Renaux, Galadrielle and Escalera, Sergio and Moeslund, Thomas B.}, title = {A Noisy Elephant in the Room: Is Your Out-of-Distribution Detector Robust to Label Noise?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22626-22636} }

VideoMAC: Video Masked Autoencoders Meet ConvNets
Gensheng Pei,
Tao Chen,
Xiruo Jiang,
Huafeng Liu,
Zeren Sun,
Yazhou Yao
[pdf] [arXiv]
[bibtex]
@InProceedings{Pei_2024_CVPR, author = {Pei, Gensheng and Chen, Tao and Jiang, Xiruo and Liu, Huafeng and Sun, Zeren and Yao, Yazhou}, title = {VideoMAC: Video Masked Autoencoders Meet ConvNets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22733-22743} }

Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes
Yujie Lu,
Long Wan,
Nayu Ding,
Yulong Wang,
Shuhan Shen,
Shen Cai,
Lin Gao
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2024_CVPR, author = {Lu, Yujie and Wan, Long and Ding, Nayu and Wang, Yulong and Shen, Shuhan and Cai, Shen and Gao, Lin}, title = {Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20551-20560} }

OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation
Bohao Peng,
Xiaoyang Wu,
Li Jiang,
Yukang Chen,
Hengshuang Zhao,
Zhuotao Tian,
Jiaya Jia
[pdf] [supp]
[bibtex]
@InProceedings{Peng_2024_CVPR, author = {Peng, Bohao and Wu, Xiaoyang and Jiang, Li and Chen, Yukang and Zhao, Hengshuang and Tian, Zhuotao and Jia, Jiaya}, title = {OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21305-21315} }

Generative Image Dynamics
Zhengqi Li,
Richard Tucker,
Noah Snavely,
Aleksander Holynski
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Zhengqi and Tucker, Richard and Snavely, Noah and Holynski, Aleksander}, title = {Generative Image Dynamics}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24142-24153} }

On the Test-Time Zero-Shot Generalization of Vision-Language Models: Do We Really Need Prompt Learning?
Maxime Zanella,
Ismail Ben Ayed
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zanella_2024_CVPR, author = {Zanella, Maxime and Ben Ayed, Ismail}, title = {On the Test-Time Zero-Shot Generalization of Vision-Language Models: Do We Really Need Prompt Learning?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23783-23793} }

Beyond Text: Frozen Large Language Models in Visual Signal Comprehension
Lei Zhu,
Fangyun Wei,
Yanye Lu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2024_CVPR, author = {Zhu, Lei and Wei, Fangyun and Lu, Yanye}, title = {Beyond Text: Frozen Large Language Models in Visual Signal Comprehension}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27047-27057} }

Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation
Sihan Liu,
Yiwei Ma,
Xiaoqing Zhang,
Haowei Wang,
Jiayi Ji,
Xiaoshuai Sun,
Rongrong Ji
[pdf] [arXiv]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Sihan and Ma, Yiwei and Zhang, Xiaoqing and Wang, Haowei and Ji, Jiayi and Sun, Xiaoshuai and Ji, Rongrong}, title = {Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26658-26668} }

GLACE: Global Local Accelerated Coordinate Encoding
Fangjinhua Wang,
Xudong Jiang,
Silvano Galliani,
Christoph Vogel,
Marc Pollefeys
[pdf] [supp]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Fangjinhua and Jiang, Xudong and Galliani, Silvano and Vogel, Christoph and Pollefeys, Marc}, title = {GLACE: Global Local Accelerated Coordinate Encoding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21562-21571} }

Localization Is All You Evaluate: Data Leakage in Online Mapping Datasets and How to Fix It
Adam Lilja,
Junsheng Fu,
Erik Stenborg,
Lars Hammarstrand
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lilja_2024_CVPR, author = {Lilja, Adam and Fu, Junsheng and Stenborg, Erik and Hammarstrand, Lars}, title = {Localization Is All You Evaluate: Data Leakage in Online Mapping Datasets and How to Fix It}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22150-22159} }

Alchemist: Parametric Control of Material Properties with Diffusion Models
Prafull Sharma,
Varun Jampani,
Yuanzhen Li,
Xuhui Jia,
Dmitry Lagun,
Fredo Durand,
Bill Freeman,
Mark Matthews
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sharma_2024_CVPR, author = {Sharma, Prafull and Jampani, Varun and Li, Yuanzhen and Jia, Xuhui and Lagun, Dmitry and Durand, Fredo and Freeman, Bill and Matthews, Mark}, title = {Alchemist: Parametric Control of Material Properties with Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24130-24141} }

MoDE: CLIP Data Experts via Clustering
Jiawei Ma,
Po-Yao Huang,
Saining Xie,
Shang-Wen Li,
Luke Zettlemoyer,
Shih-Fu Chang,
Wen-Tau Yih,
Hu Xu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2024_CVPR, author = {Ma, Jiawei and Huang, Po-Yao and Xie, Saining and Li, Shang-Wen and Zettlemoyer, Luke and Chang, Shih-Fu and Yih, Wen-Tau and Xu, Hu}, title = {MoDE: CLIP Data Experts via Clustering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26354-26363} }

FineSports: A Multi-person Hierarchical Sports Video Dataset for Fine-grained Action Understanding
Jinglin Xu,
Guohao Zhao,
Sibo Yin,
Wenhao Zhou,
Yuxin Peng
[pdf] [supp]
[bibtex]
@InProceedings{Xu_2024_CVPR, author = {Xu, Jinglin and Zhao, Guohao and Yin, Sibo and Zhou, Wenhao and Peng, Yuxin}, title = {FineSports: A Multi-person Hierarchical Sports Video Dataset for Fine-grained Action Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21773-21782} }

GARField: Group Anything with Radiance Fields
Chung Min Kim,
Mingxuan Wu,
Justin Kerr,
Ken Goldberg,
Matthew Tancik,
Angjoo Kanazawa
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_CVPR, author = {Kim, Chung Min and Wu, Mingxuan and Kerr, Justin and Goldberg, Ken and Tancik, Matthew and Kanazawa, Angjoo}, title = {GARField: Group Anything with Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21530-21539} }

Learning Equi-angular Representations for Online Continual Learning
Minhyuk Seo,
Hyunseo Koh,
Wonje Jeung,
Minjae Lee,
San Kim,
Hankook Lee,
Sungjun Cho,
Sungik Choi,
Hyunwoo Kim,
Jonghyun Choi
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Seo_2024_CVPR, author = {Seo, Minhyuk and Koh, Hyunseo and Jeung, Wonje and Lee, Minjae and Kim, San and Lee, Hankook and Cho, Sungjun and Choi, Sungik and Kim, Hyunwoo and Choi, Jonghyun}, title = {Learning Equi-angular Representations for Online Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23933-23942} }

POCE: Primal Policy Optimization with Conservative Estimation for Multi-constraint Offline Reinforcement Learning
Jiayi Guan,
Li Shen,
Ao Zhou,
Lusong Li,
Han Hu,
Xiaodong He,
Guang Chen,
Changjun Jiang
[pdf] [supp]
[bibtex]
@InProceedings{Guan_2024_CVPR, author = {Guan, Jiayi and Shen, Li and Zhou, Ao and Li, Lusong and Hu, Han and He, Xiaodong and Chen, Guang and Jiang, Changjun}, title = {POCE: Primal Policy Optimization with Conservative Estimation for Multi-constraint Offline Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26243-26253} }

Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement
Jinyoung Jun,
Jae-Han Lee,
Chang-Su Kim
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jun_2024_CVPR, author = {Jun, Jinyoung and Lee, Jae-Han and Kim, Chang-Su}, title = {Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19768-19778} }

C3Net: Compound Conditioned ControlNet for Multimodal Content Generation
Juntao Zhang,
Yuehuai Liu,
Yu-Wing Tai,
Chi-Keung Tang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Juntao and Liu, Yuehuai and Tai, Yu-Wing and Tang, Chi-Keung}, title = {C3Net: Compound Conditioned ControlNet for Multimodal Content Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26886-26895} }

Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentation
Jonas Herzog
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Herzog_2024_CVPR, author = {Herzog, Jonas}, title = {Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23605-23615} }

Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding
Hoang-Quan Nguyen,
Thanh-Dat Truong,
Xuan Bac Nguyen,
Ashley Dowling,
Xin Li,
Khoa Luu
[pdf] [supp]
[bibtex]
@InProceedings{Nguyen_2024_CVPR, author = {Nguyen, Hoang-Quan and Truong, Thanh-Dat and Nguyen, Xuan Bac and Dowling, Ashley and Li, Xin and Luu, Khoa}, title = {Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21945-21955} }

Data-Efficient Multimodal Fusion on a Single GPU
Noël Vouitsis,
Zhaoyan Liu,
Satya Krishna Gorti,
Valentin Villecroze,
Jesse C. Cresswell,
Guangwei Yu,
Gabriel Loaiza-Ganem,
Maksims Volkovs
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Vouitsis_2024_CVPR, author = {Vouitsis, No\"el and Liu, Zhaoyan and Gorti, Satya Krishna and Villecroze, Valentin and Cresswell, Jesse C. and Yu, Guangwei and Loaiza-Ganem, Gabriel and Volkovs, Maksims}, title = {Data-Efficient Multimodal Fusion on a Single GPU}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27239-27251} }

FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning
Rishub Tamirisa,
Chulin Xie,
Wenxuan Bao,
Andy Zhou,
Ron Arel,
Aviv Shamsian
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tamirisa_2024_CVPR, author = {Tamirisa, Rishub and Xie, Chulin and Bao, Wenxuan and Zhou, Andy and Arel, Ron and Shamsian, Aviv}, title = {FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23985-23994} }

Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining
Xiang Chen,
Jinshan Pan,
Jiangxin Dong
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Xiang and Pan, Jinshan and Dong, Jiangxin}, title = {Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25627-25636} }

Enhancing Quality of Compressed Images by Mitigating Enhancement Bias Towards Compression Domain
Qunliang Xing,
Mai Xu,
Shengxi Li,
Xin Deng,
Meisong Zheng,
Huaida Liu,
Ying Chen
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xing_2024_CVPR, author = {Xing, Qunliang and Xu, Mai and Li, Shengxi and Deng, Xin and Zheng, Meisong and Liu, Huaida and Chen, Ying}, title = {Enhancing Quality of Compressed Images by Mitigating Enhancement Bias Towards Compression Domain}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25501-25511} }

LangSplat: 3D Language Gaussian Splatting
Minghan Qin,
Wanhua Li,
Jiawei Zhou,
Haoqian Wang,
Hanspeter Pfister
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qin_2024_CVPR, author = {Qin, Minghan and Li, Wanhua and Zhou, Jiawei and Wang, Haoqian and Pfister, Hanspeter}, title = {LangSplat: 3D Language Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20051-20060} }

Improving Spectral Snapshot Reconstruction with Spectral-Spatial Rectification
Jiancheng Zhang,
Haijin Zeng,
Yongyong Chen,
Dengxiu Yu,
Yin-Ping Zhao
[pdf]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Jiancheng and Zeng, Haijin and Chen, Yongyong and Yu, Dengxiu and Zhao, Yin-Ping}, title = {Improving Spectral Snapshot Reconstruction with Spectral-Spatial Rectification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25817-25826} }

DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization
Jiahe Li,
Jiawei Zhang,
Xiao Bai,
Jin Zheng,
Xin Ning,
Jun Zhou,
Lin Gu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Jiahe and Zhang, Jiawei and Bai, Xiao and Zheng, Jin and Ning, Xin and Zhou, Jun and Gu, Lin}, title = {DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20775-20785} }

ColorPCR: Color Point Cloud Registration with Multi-Stage Geometric-Color Fusion
Juncheng Mu,
Lin Bie,
Shaoyi Du,
Yue Gao
[pdf] [supp]
[bibtex]
@InProceedings{Mu_2024_CVPR, author = {Mu, Juncheng and Bie, Lin and Du, Shaoyi and Gao, Yue}, title = {ColorPCR: Color Point Cloud Registration with Multi-Stage Geometric-Color Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21061-21070} }

HomoFormer: Homogenized Transformer for Image Shadow Removal
Jie Xiao,
Xueyang Fu,
Yurui Zhu,
Dong Li,
Jie Huang,
Kai Zhu,
Zheng-Jun Zha
[pdf] [supp]
[bibtex]
@InProceedings{Xiao_2024_CVPR, author = {Xiao, Jie and Fu, Xueyang and Zhu, Yurui and Li, Dong and Huang, Jie and Zhu, Kai and Zha, Zheng-Jun}, title = {HomoFormer: Homogenized Transformer for Image Shadow Removal}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25617-25626} }

What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models
Letian Zhang,
Xiaotong Zhai,
Zhongkai Zhao,
Yongshuo Zong,
Xin Wen,
Bingchen Zhao
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Letian and Zhai, Xiaotong and Zhao, Zhongkai and Zong, Yongshuo and Wen, Xin and Zhao, Bingchen}, title = {What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21853-21862} }

FAR: Flexible Accurate and Robust 6DoF Relative Camera Pose Estimation
Chris Rockwell,
Nilesh Kulkarni,
Linyi Jin,
Jeong Joon Park,
Justin Johnson,
David F. Fouhey
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rockwell_2024_CVPR, author = {Rockwell, Chris and Kulkarni, Nilesh and Jin, Linyi and Park, Jeong Joon and Johnson, Justin and Fouhey, David F.}, title = {FAR: Flexible Accurate and Robust 6DoF Relative Camera Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19854-19864} }

eTraM: Event-based Traffic Monitoring Dataset
Aayush Atul Verma,
Bharatesh Chakravarthi,
Arpitsinh Vaghela,
Hua Wei,
Yezhou Yang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Verma_2024_CVPR, author = {Verma, Aayush Atul and Chakravarthi, Bharatesh and Vaghela, Arpitsinh and Wei, Hua and Yang, Yezhou}, title = {eTraM: Event-based Traffic Monitoring Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22637-22646} }

MoCha-Stereo: Motif Channel Attention Network for Stereo Matching
Ziyang Chen,
Wei Long,
He Yao,
Yongjun Zhang,
Bingshu Wang,
Yongbin Qin,
Jia Wu
[pdf] [supp]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Ziyang and Long, Wei and Yao, He and Zhang, Yongjun and Wang, Bingshu and Qin, Yongbin and Wu, Jia}, title = {MoCha-Stereo: Motif Channel Attention Network for Stereo Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27768-27777} }

Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension
Quan Liu,
Hongzi Zhu,
Zhenxi Wang,
Yunsong Zhou,
Shan Chang,
Minyi Guo
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Quan and Zhu, Hongzi and Wang, Zhenxi and Zhou, Yunsong and Chang, Shan and Guo, Minyi}, title = {Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20816-20826} }

Multi-modal Learning for Geospatial Vegetation Forecasting
Vitus Benson,
Claire Robin,
Christian Requena-Mesa,
Lazaro Alonso,
Nuno Carvalhais,
José Cortés,
Zhihan Gao,
Nora Linscheid,
Mélanie Weynants,
Markus Reichstein
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Benson_2024_CVPR, author = {Benson, Vitus and Robin, Claire and Requena-Mesa, Christian and Alonso, Lazaro and Carvalhais, Nuno and Cort\'es, Jos\'e and Gao, Zhihan and Linscheid, Nora and Weynants, M\'elanie and Reichstein, Markus}, title = {Multi-modal Learning for Geospatial Vegetation Forecasting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27788-27799} }

Bring Event into RGB and LiDAR: Hierarchical Visual-Motion Fusion for Scene Flow
Hanyu Zhou,
Yi Chang,
Zhiwei Shi
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2024_CVPR, author = {Zhou, Hanyu and Chang, Yi and Shi, Zhiwei}, title = {Bring Event into RGB and LiDAR: Hierarchical Visual-Motion Fusion for Scene Flow}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26477-26486} }

MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors
He Zhang,
Shenghao Ren,
Haolei Yuan,
Jianhui Zhao,
Fan Li,
Shuangpeng Sun,
Zhenghao Liang,
Tao Yu,
Qiu Shen,
Xun Cao
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, He and Ren, Shenghao and Yuan, Haolei and Zhao, Jianhui and Li, Fan and Sun, Shuangpeng and Liang, Zhenghao and Yu, Tao and Shen, Qiu and Cao, Xun}, title = {MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21842-21852} }

JoAPR: Cleaning the Lens of Prompt Learning for Vision-Language Models
Yuncheng Guo,
Xiaodong Gu
[pdf] [supp]
[bibtex]
@InProceedings{Guo_2024_CVPR, author = {Guo, Yuncheng and Gu, Xiaodong}, title = {JoAPR: Cleaning the Lens of Prompt Learning for Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28695-28705} }

Open-Vocabulary 3D Semantic Segmentation with Foundation Models
Li Jiang,
Shaoshuai Shi,
Bernt Schiele
[pdf]
[bibtex]
@InProceedings{Jiang_2024_CVPR, author = {Jiang, Li and Shi, Shaoshuai and Schiele, Bernt}, title = {Open-Vocabulary 3D Semantic Segmentation with Foundation Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21284-21294} }

1-Lipschitz Layers Compared: Memory Speed and Certifiable Robustness
Bernd Prach,
Fabio Brau,
Giorgio Buttazzo,
Christoph H. Lampert
[pdf] [supp]
[bibtex]
@InProceedings{Prach_2024_CVPR, author = {Prach, Bernd and Brau, Fabio and Buttazzo, Giorgio and Lampert, Christoph H.}, title = {1-Lipschitz Layers Compared: Memory Speed and Certifiable Robustness}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24574-24583} }

Construct to Associate: Cooperative Context Learning for Domain Adaptive Point Cloud Segmentation
Guangrui Li
[pdf] [supp]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Guangrui}, title = {Construct to Associate: Cooperative Context Learning for Domain Adaptive Point Cloud Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27917-27926} }

GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo
Jiang Wu,
Rui Li,
Haofei Xu,
Wenxun Zhao,
Yu Zhu,
Jinqiu Sun,
Yanning Zhang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2024_CVPR, author = {Wu, Jiang and Li, Rui and Xu, Haofei and Zhao, Wenxun and Zhu, Yu and Sun, Jinqiu and Zhang, Yanning}, title = {GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20207-20216} }

Evaluating Transferability in Retrieval Tasks: An Approach Using MMD and Kernel Methods
Mengyu Dai,
Amir Hossein Raffiee,
Aashish Jain,
Joshua Correa
[pdf] [supp]
[bibtex]
@InProceedings{Dai_2024_CVPR, author = {Dai, Mengyu and Raffiee, Amir Hossein and Jain, Aashish and Correa, Joshua}, title = {Evaluating Transferability in Retrieval Tasks: An Approach Using MMD and Kernel Methods}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22390-22400} }

OMG-Seg: Is One Model Good Enough For All Segmentation?
Xiangtai Li,
Haobo Yuan,
Wei Li,
Henghui Ding,
Size Wu,
Wenwei Zhang,
Yining Li,
Kai Chen,
Chen Change Loy
[pdf] [supp]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Xiangtai and Yuan, Haobo and Li, Wei and Ding, Henghui and Wu, Size and Zhang, Wenwei and Li, Yining and Chen, Kai and Loy, Chen Change}, title = {OMG-Seg: Is One Model Good Enough For All Segmentation?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27948-27959} }

DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection
Lewei Yao,
Renjie Pi,
Jianhua Han,
Xiaodan Liang,
Hang Xu,
Wei Zhang,
Zhenguo Li,
Dan Xu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yao_2024_CVPR, author = {Yao, Lewei and Pi, Renjie and Han, Jianhua and Liang, Xiaodan and Xu, Hang and Zhang, Wei and Li, Zhenguo and Xu, Dan}, title = {DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27391-27401} }

UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement
Yaofeng Xie,
Lingwei Kong,
Kai Chen,
Ziqiang Zheng,
Xiao Yu,
Zhibin Yu,
Bing Zheng
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xie_2024_CVPR, author = {Xie, Yaofeng and Kong, Lingwei and Chen, Kai and Zheng, Ziqiang and Yu, Xiao and Yu, Zhibin and Zheng, Bing}, title = {UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22358-22367} }

Discovering Syntactic Interaction Clues for Human-Object Interaction Detection
Jinguo Luo,
Weihong Ren,
Weibo Jiang,
Xi'ai Chen,
Qiang Wang,
Zhi Han,
Honghai Liu
[pdf]
[bibtex]
@InProceedings{Luo_2024_CVPR, author = {Luo, Jinguo and Ren, Weihong and Jiang, Weibo and Chen, Xi'ai and Wang, Qiang and Han, Zhi and Liu, Honghai}, title = {Discovering Syntactic Interaction Clues for Human-Object Interaction Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28212-28222} }

Inter-X: Towards Versatile Human-Human Interaction Analysis
Liang Xu,
Xintao Lv,
Yichao Yan,
Xin Jin,
Shuwen Wu,
Congsheng Xu,
Yifan Liu,
Yizhou Zhou,
Fengyun Rao,
Xingdong Sheng,
Yunhui Liu,
Wenjun Zeng,
Xiaokang Yang
[pdf] [supp]
[bibtex]
@InProceedings{Xu_2024_CVPR, author = {Xu, Liang and Lv, Xintao and Yan, Yichao and Jin, Xin and Wu, Shuwen and Xu, Congsheng and Liu, Yifan and Zhou, Yizhou and Rao, Fengyun and Sheng, Xingdong and Liu, Yunhui and Zeng, Wenjun and Yang, Xiaokang}, title = {Inter-X: Towards Versatile Human-Human Interaction Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22260-22271} }

MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation
Mi Yan,
Jiazhao Zhang,
Yan Zhu,
He Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yan_2024_CVPR, author = {Yan, Mi and Zhang, Jiazhao and Zhu, Yan and Wang, He}, title = {MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28274-28284} }

PeerAiD: Improving Adversarial Distillation from a Specialized Peer Tutor
Jaewon Jung,
Hongsun Jang,
Jaeyong Song,
Jinho Lee
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jung_2024_CVPR, author = {Jung, Jaewon and Jang, Hongsun and Song, Jaeyong and Lee, Jinho}, title = {PeerAiD: Improving Adversarial Distillation from a Specialized Peer Tutor}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24482-24491} }

Scaling Laws for Data Filtering-- Data Curation cannot be Compute Agnostic
Sachin Goyal,
Pratyush Maini,
Zachary C. Lipton,
Aditi Raghunathan,
J. Zico Kolter
[pdf] [supp]
[bibtex]
@InProceedings{Goyal_2024_CVPR, author = {Goyal, Sachin and Maini, Pratyush and Lipton, Zachary C. and Raghunathan, Aditi and Kolter, J. Zico}, title = {Scaling Laws for Data Filtering-- Data Curation cannot be Compute Agnostic}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22702-22711} }

Beyond Average: Individualized Visual Scanpath Prediction
Xianyu Chen,
Ming Jiang,
Qi Zhao
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Xianyu and Jiang, Ming and Zhao, Qi}, title = {Beyond Average: Individualized Visual Scanpath Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25420-25431} }

Seeing Motion at Nighttime with an Event Camera
Haoyue Liu,
Shihan Peng,
Lin Zhu,
Yi Chang,
Hanyu Zhou,
Luxin Yan
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Haoyue and Peng, Shihan and Zhu, Lin and Chang, Yi and Zhou, Hanyu and Yan, Luxin}, title = {Seeing Motion at Nighttime with an Event Camera}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25648-25658} }

FISBe: A Real-World Benchmark Dataset for Instance Segmentation of Long-Range Thin Filamentous Structures
Lisa Mais,
Peter Hirsch,
Claire Managan,
Ramya Kandarpa,
Josef Lorenz Rumberger,
Annika Reinke,
Lena Maier-Hein,
Gudrun Ihrke,
Dagmar Kainmueller
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mais_2024_CVPR, author = {Mais, Lisa and Hirsch, Peter and Managan, Claire and Kandarpa, Ramya and Rumberger, Josef Lorenz and Reinke, Annika and Maier-Hein, Lena and Ihrke, Gudrun and Kainmueller, Dagmar}, title = {FISBe: A Real-World Benchmark Dataset for Instance Segmentation of Long-Range Thin Filamentous Structures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22249-22259} }

LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding Reasoning and Planning
Sijin Chen,
Xin Chen,
Chi Zhang,
Mingsheng Li,
Gang Yu,
Hao Fei,
Hongyuan Zhu,
Jiayuan Fan,
Tao Chen
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Sijin and Chen, Xin and Zhang, Chi and Li, Mingsheng and Yu, Gang and Fei, Hao and Zhu, Hongyuan and Fan, Jiayuan and Chen, Tao}, title = {LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding Reasoning and Planning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26428-26438} }

4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
Guanjun Wu,
Taoran Yi,
Jiemin Fang,
Lingxi Xie,
Xiaopeng Zhang,
Wei Wei,
Wenyu Liu,
Qi Tian,
Xinggang Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2024_CVPR, author = {Wu, Guanjun and Yi, Taoran and Fang, Jiemin and Xie, Lingxi and Zhang, Xiaopeng and Wei, Wei and Liu, Wenyu and Tian, Qi and Wang, Xinggang}, title = {4D Gaussian Splatting for Real-Time Dynamic Scene Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20310-20320} }

Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching
Xianqi Wang,
Gangwei Xu,
Hao Jia,
Xin Yang
[pdf] [supp]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Xianqi and Xu, Gangwei and Jia, Hao and Yang, Xin}, title = {Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19701-19710} }

PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees
Chulin Xie,
De-An Huang,
Wenda Chu,
Daguang Xu,
Chaowei Xiao,
Bo Li,
Anima Anandkumar
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xie_2024_CVPR, author = {Xie, Chulin and Huang, De-An and Chu, Wenda and Xu, Daguang and Xiao, Chaowei and Li, Bo and Anandkumar, Anima}, title = {PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23838-23848} }

MAFA: Managing False Negatives for Vision-Language Pre-training
Jaeseok Byun,
Dohoon Kim,
Taesup Moon
[pdf] [supp]
[bibtex]
@InProceedings{Byun_2024_CVPR, author = {Byun, Jaeseok and Kim, Dohoon and Moon, Taesup}, title = {MAFA: Managing False Negatives for Vision-Language Pre-training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27314-27324} }

InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning
Yan-Shuo Liang,
Wu-Jun Li
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liang_2024_CVPR, author = {Liang, Yan-Shuo and Li, Wu-Jun}, title = {InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23638-23647} }

PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustment
Tianchen Deng,
Guole Shen,
Tong Qin,
Jianyu Wang,
Wentao Zhao,
Jingchuan Wang,
Danwei Wang,
Weidong Chen
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Deng_2024_CVPR, author = {Deng, Tianchen and Shen, Guole and Qin, Tong and Wang, Jianyu and Zhao, Wentao and Wang, Jingchuan and Wang, Danwei and Chen, Weidong}, title = {PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19657-19666} }

Multi-Task Dense Prediction via Mixture of Low-Rank Experts
Yuqi Yang,
Peng-Tao Jiang,
Qibin Hou,
Hao Zhang,
Jinwei Chen,
Bo Li
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2024_CVPR, author = {Yang, Yuqi and Jiang, Peng-Tao and Hou, Qibin and Zhang, Hao and Chen, Jinwei and Li, Bo}, title = {Multi-Task Dense Prediction via Mixture of Low-Rank Experts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27927-27937} }

Binding Touch to Everything: Learning Unified Multimodal Tactile Representations
Fengyu Yang,
Chao Feng,
Ziyang Chen,
Hyoungseob Park,
Daniel Wang,
Yiming Dou,
Ziyao Zeng,
Xien Chen,
Rit Gangopadhyay,
Andrew Owens,
Alex Wong
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2024_CVPR, author = {Yang, Fengyu and Feng, Chao and Chen, Ziyang and Park, Hyoungseob and Wang, Daniel and Dou, Yiming and Zeng, Ziyao and Chen, Xien and Gangopadhyay, Rit and Owens, Andrew and Wong, Alex}, title = {Binding Touch to Everything: Learning Unified Multimodal Tactile Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26340-26353} }

Your Transferability Barrier is Fragile: Free-Lunch for Transferring the Non-Transferable Learning
Ziming Hong,
Li Shen,
Tongliang Liu
[pdf] [supp]
[bibtex]
@InProceedings{Hong_2024_CVPR, author = {Hong, Ziming and Shen, Li and Liu, Tongliang}, title = {Your Transferability Barrier is Fragile: Free-Lunch for Transferring the Non-Transferable Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28805-28815} }

Complementing Event Streams and RGB Frames for Hand Mesh Reconstruction
Jianping Jiang,
Xinyu Zhou,
Bingxuan Wang,
Xiaoming Deng,
Chao Xu,
Boxin Shi
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2024_CVPR, author = {Jiang, Jianping and Zhou, Xinyu and Wang, Bingxuan and Deng, Xiaoming and Xu, Chao and Shi, Boxin}, title = {Complementing Event Streams and RGB Frames for Hand Mesh Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24944-24954} }

Empowering Resampling Operation for Ultra-High-Definition Image Enhancement with Model-Aware Guidance
Wei Yu,
Jie Huang,
Bing Li,
Kaiwen Zheng,
Qi Zhu,
Man Zhou,
Feng Zhao
[pdf] [supp]
[bibtex]
@InProceedings{Yu_2024_CVPR, author = {Yu, Wei and Huang, Jie and Li, Bing and Zheng, Kaiwen and Zhu, Qi and Zhou, Man and Zhao, Feng}, title = {Empowering Resampling Operation for Ultra-High-Definition Image Enhancement with Model-Aware Guidance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25722-25731} }

Hallucination Augmented Contrastive Learning for Multimodal Large Language Model
Chaoya Jiang,
Haiyang Xu,
Mengfan Dong,
Jiaxing Chen,
Wei Ye,
Ming Yan,
Qinghao Ye,
Ji Zhang,
Fei Huang,
Shikun Zhang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2024_CVPR, author = {Jiang, Chaoya and Xu, Haiyang and Dong, Mengfan and Chen, Jiaxing and Ye, Wei and Yan, Ming and Ye, Qinghao and Zhang, Ji and Huang, Fei and Zhang, Shikun}, title = {Hallucination Augmented Contrastive Learning for Multimodal Large Language Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27036-27046} }

Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation
Qi Yang,
Xing Nie,
Tong Li,
Pengfei Gao,
Ying Guo,
Cheng Zhen,
Pengfei Yan,
Shiming Xiang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2024_CVPR, author = {Yang, Qi and Nie, Xing and Li, Tong and Gao, Pengfei and Guo, Ying and Zhen, Cheng and Yan, Pengfei and Xiang, Shiming}, title = {Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27134-27143} }

Improved Self-Training for Test-Time Adaptation
Jing Ma
[pdf] [supp]
[bibtex]
@InProceedings{Ma_2024_CVPR, author = {Ma, Jing}, title = {Improved Self-Training for Test-Time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23701-23710} }

Unsupervised Feature Learning with Emergent Data-Driven Prototypicality
Yunhui Guo,
Youren Zhang,
Yubei Chen,
Stella X. Yu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2024_CVPR, author = {Guo, Yunhui and Zhang, Youren and Chen, Yubei and Yu, Stella X.}, title = {Unsupervised Feature Learning with Emergent Data-Driven Prototypicality}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23199-23208} }

Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names
Yapeng Li,
Yong Luo,
Zengmao Wang,
Bo Du
[pdf] [supp]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Yapeng and Luo, Yong and Wang, Zengmao and Du, Bo}, title = {Improving Generalized Zero-Shot Learning by Exploring the Diverse Semantics from External Class Names}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23344-23353} }

TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes
Xuying Zhang,
Bo-Wen Yin,
Yuming Chen,
Zheng Lin,
Yunheng Li,
Qibin Hou,
Ming-Ming Cheng
[pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Xuying and Yin, Bo-Wen and Chen, Yuming and Lin, Zheng and Li, Yunheng and Hou, Qibin and Cheng, Ming-Ming}, title = {TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19531-19540} }

GSNeRF: Generalizable Semantic Neural Radiance Fields with Enhanced 3D Scene Understanding
Zi-Ting Chou,
Sheng-Yu Huang,
I-Jieh Liu,
Yu-Chiang Frank Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chou_2024_CVPR, author = {Chou, Zi-Ting and Huang, Sheng-Yu and Liu, I-Jieh and Wang, Yu-Chiang Frank}, title = {GSNeRF: Generalizable Semantic Neural Radiance Fields with Enhanced 3D Scene Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20806-20815} }

Alpha Invariance: On Inverse Scaling Between Distance and Volume Density in Neural Radiance Fields
Joshua Ahn,
Haochen Wang,
Raymond A. Yeh,
Greg Shakhnarovich
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ahn_2024_CVPR, author = {Ahn, Joshua and Wang, Haochen and Yeh, Raymond A. and Shakhnarovich, Greg}, title = {Alpha Invariance: On Inverse Scaling Between Distance and Volume Density in Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20396-20405} }

D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection
Dinh Phat Do,
Taehoon Kim,
Jaemin Na,
Jiwon Kim,
Keonho Lee,
Kyunghwan Cho,
Wonjun Hwang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Do_2024_CVPR, author = {Do, Dinh Phat and Kim, Taehoon and Na, Jaemin and Kim, Jiwon and Lee, Keonho and Cho, Kyunghwan and Hwang, Wonjun}, title = {D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23313-23322} }

Positive-Unlabeled Learning by Latent Group-Aware Meta Disambiguation
Lin Long,
Haobo Wang,
Zhijie Jiang,
Lei Feng,
Chang Yao,
Gang Chen,
Junbo Zhao
[pdf] [supp]
[bibtex]
@InProceedings{Long_2024_CVPR, author = {Long, Lin and Wang, Haobo and Jiang, Zhijie and Feng, Lei and Yao, Chang and Chen, Gang and Zhao, Junbo}, title = {Positive-Unlabeled Learning by Latent Group-Aware Meta Disambiguation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23138-23147} }

Linguistic-Aware Patch Slimming Framework for Fine-grained Cross-Modal Alignment
Zheren Fu,
Lei Zhang,
Hou Xia,
Zhendong Mao
[pdf]
[bibtex]
@InProceedings{Fu_2024_CVPR, author = {Fu, Zheren and Zhang, Lei and Xia, Hou and Mao, Zhendong}, title = {Linguistic-Aware Patch Slimming Framework for Fine-grained Cross-Modal Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26307-26316} }

Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentation
Jiapeng Su,
Qi Fan,
Wenjie Pei,
Guangming Lu,
Fanglin Chen
[pdf] [arXiv]
[bibtex]
@InProceedings{Su_2024_CVPR, author = {Su, Jiapeng and Fan, Qi and Pei, Wenjie and Lu, Guangming and Chen, Fanglin}, title = {Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24036-24045} }

CPP-Net: Embracing Multi-Scale Feature Fusion into Deep Unfolding CP-PPA Network for Compressive Sensing
Zhen Guo,
Hongping Gan
[pdf] [supp]
[bibtex]
@InProceedings{Guo_2024_CVPR, author = {Guo, Zhen and Gan, Hongping}, title = {CPP-Net: Embracing Multi-Scale Feature Fusion into Deep Unfolding CP-PPA Network for Compressive Sensing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25086-25095} }

3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos
Jiakai Sun,
Han Jiao,
Guangyuan Li,
Zhanjie Zhang,
Lei Zhao,
Wei Xing
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2024_CVPR, author = {Sun, Jiakai and Jiao, Han and Li, Guangyuan and Zhang, Zhanjie and Zhao, Lei and Xing, Wei}, title = {3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20675-20685} }

FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models
Shivangi Aneja,
Justus Thies,
Angela Dai,
Matthias Nießner
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Aneja_2024_CVPR, author = {Aneja, Shivangi and Thies, Justus and Dai, Angela and Nie{\ss}ner, Matthias}, title = {FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21263-21273} }

Mip-Splatting: Alias-free 3D Gaussian Splatting
Zehao Yu,
Anpei Chen,
Binbin Huang,
Torsten Sattler,
Andreas Geiger
[pdf] [supp]
[bibtex]
@InProceedings{Yu_2024_CVPR, author = {Yu, Zehao and Chen, Anpei and Huang, Binbin and Sattler, Torsten and Geiger, Andreas}, title = {Mip-Splatting: Alias-free 3D Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19447-19456} }

Learning Coupled Dictionaries from Unpaired Data for Image Super-Resolution
Longguang Wang,
Juncheng Li,
Yingqian Wang,
Qingyong Hu,
Yulan Guo
[pdf]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Longguang and Li, Juncheng and Wang, Yingqian and Hu, Qingyong and Guo, Yulan}, title = {Learning Coupled Dictionaries from Unpaired Data for Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25712-25721} }

Deep Video Inverse Tone Mapping Based on Temporal Clues
Yuyao Ye,
Ning Zhang,
Yang Zhao,
Hongbin Cao,
Ronggang Wang
[pdf] [supp]
[bibtex]
@InProceedings{Ye_2024_CVPR, author = {Ye, Yuyao and Zhang, Ning and Zhao, Yang and Cao, Hongbin and Wang, Ronggang}, title = {Deep Video Inverse Tone Mapping Based on Temporal Clues}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25995-26004} }

NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentation
Jiahao Chen,
Yipeng Qin,
Lingjie Liu,
Jiangbo Lu,
Guanbin Li
[pdf] [supp]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Jiahao and Qin, Yipeng and Liu, Lingjie and Lu, Jiangbo and Li, Guanbin}, title = {NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19436-19446} }

ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object
Chenshuang Zhang,
Fei Pan,
Junmo Kim,
In So Kweon,
Chengzhi Mao
[pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Chenshuang and Pan, Fei and Kim, Junmo and Kweon, In So and Mao, Chengzhi}, title = {ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21752-21762} }

Text-Enhanced Data-free Approach for Federated Class-Incremental Learning
Minh-Tuan Tran,
Trung Le,
Xuan-May Le,
Mehrtash Harandi,
Dinh Phung
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tran_2024_CVPR, author = {Tran, Minh-Tuan and Le, Trung and Le, Xuan-May and Harandi, Mehrtash and Phung, Dinh}, title = {Text-Enhanced Data-free Approach for Federated Class-Incremental Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23870-23880} }

UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusion
Junsheng Zhou,
Weiqi Zhang,
Baorui Ma,
Kanle Shi,
Yu-Shen Liu,
Zhizhong Han
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2024_CVPR, author = {Zhou, Junsheng and Zhang, Weiqi and Ma, Baorui and Shi, Kanle and Liu, Yu-Shen and Han, Zhizhong}, title = {UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21496-21506} }

Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training
Xiaoyang Wu,
Zhuotao Tian,
Xin Wen,
Bohao Peng,
Xihui Liu,
Kaicheng Yu,
Hengshuang Zhao
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2024_CVPR, author = {Wu, Xiaoyang and Tian, Zhuotao and Wen, Xin and Peng, Bohao and Liu, Xihui and Yu, Kaicheng and Zhao, Hengshuang}, title = {Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19551-19562} }

EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI
Tai Wang,
Xiaohan Mao,
Chenming Zhu,
Runsen Xu,
Ruiyuan Lyu,
Peisen Li,
Xiao Chen,
Wenwei Zhang,
Kai Chen,
Tianfan Xue,
Xihui Liu,
Cewu Lu,
Dahua Lin,
Jiangmiao Pang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Tai and Mao, Xiaohan and Zhu, Chenming and Xu, Runsen and Lyu, Ruiyuan and Li, Peisen and Chen, Xiao and Zhang, Wenwei and Chen, Kai and Xue, Tianfan and Liu, Xihui and Lu, Cewu and Lin, Dahua and Pang, Jiangmiao}, title = {EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19757-19767} }

SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild
Andreas Engelhardt,
Amit Raj,
Mark Boss,
Yunzhi Zhang,
Abhishek Kar,
Yuanzhen Li,
Deqing Sun,
Ricardo Martin Brualla,
Jonathan T. Barron,
Hendrik P. A. Lensch,
Varun Jampani
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Engelhardt_2024_CVPR, author = {Engelhardt, Andreas and Raj, Amit and Boss, Mark and Zhang, Yunzhi and Kar, Abhishek and Li, Yuanzhen and Sun, Deqing and Brualla, Ricardo Martin and Barron, Jonathan T. and Lensch, Hendrik P. A. and Jampani, Varun}, title = {SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19636-19646} }

ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations
Yuanhang Zhang,
Shuang Yang,
Shiguang Shan,
Xilin Chen
[pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Yuanhang and Yang, Shuang and Shan, Shiguang and Chen, Xilin}, title = {ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27069-27079} }

Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking
Wei Cao,
Chang Luo,
Biao Zhang,
Matthias Nießner,
Jiapeng Tang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cao_2024_CVPR, author = {Cao, Wei and Luo, Chang and Zhang, Biao and Nie{\ss}ner, Matthias and Tang, Jiapeng}, title = {Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20496-20506} }

A2XP: Towards Private Domain Generalization
Geunhyeok Yu,
Hyoseok Hwang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2024_CVPR, author = {Yu, Geunhyeok and Hwang, Hyoseok}, title = {A2XP: Towards Private Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23544-23553} }

Active Domain Adaptation with False Negative Prediction for Object Detection
Yuzuru Nakamura,
Yasunori Ishii,
Takayoshi Yamashita
[pdf] [supp]
[bibtex]
@InProceedings{Nakamura_2024_CVPR, author = {Nakamura, Yuzuru and Ishii, Yasunori and Yamashita, Takayoshi}, title = {Active Domain Adaptation with False Negative Prediction for Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28782-28792} }

Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing
Bi'an Du,
Xiang Gao,
Wei Hu,
Renjie Liao
[pdf] [arXiv]
[bibtex]
@InProceedings{Du_2024_CVPR, author = {Du, Bi'an and Gao, Xiang and Hu, Wei and Liao, Renjie}, title = {Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20850-20859} }

Benchmarking Segmentation Models with Mask-Preserved Attribute Editing
Zijin Yin,
Kongming Liang,
Bing Li,
Zhanyu Ma,
Jun Guo
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yin_2024_CVPR, author = {Yin, Zijin and Liang, Kongming and Li, Bing and Ma, Zhanyu and Guo, Jun}, title = {Benchmarking Segmentation Models with Mask-Preserved Attribute Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22509-22519} }

Analyzing and Improving the Training Dynamics of Diffusion Models
Tero Karras,
Miika Aittala,
Jaakko Lehtinen,
Janne Hellsten,
Timo Aila,
Samuli Laine
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Karras_2024_CVPR, author = {Karras, Tero and Aittala, Miika and Lehtinen, Jaakko and Hellsten, Janne and Aila, Timo and Laine, Samuli}, title = {Analyzing and Improving the Training Dynamics of Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24174-24184} }

Hierarchical Correlation Clustering and Tree Preserving Embedding
Morteza Haghir Chehreghani,
Mostafa Haghir Chehreghani
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chehreghani_2024_CVPR, author = {Chehreghani, Morteza Haghir and Chehreghani, Mostafa Haghir}, title = {Hierarchical Correlation Clustering and Tree Preserving Embedding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23083-23093} }

Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?
Zhengyue Zhao,
Jinhao Duan,
Kaidi Xu,
Chenan Wang,
Rui Zhang,
Zidong Du,
Qi Guo,
Xing Hu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2024_CVPR, author = {Zhao, Zhengyue and Duan, Jinhao and Xu, Kaidi and Wang, Chenan and Zhang, Rui and Du, Zidong and Guo, Qi and Hu, Xing}, title = {Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24398-24407} }

MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World
Yining Hong,
Zishuo Zheng,
Peihao Chen,
Yian Wang,
Junyan Li,
Chuang Gan
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hong_2024_CVPR, author = {Hong, Yining and Zheng, Zishuo and Chen, Peihao and Wang, Yian and Li, Junyan and Gan, Chuang}, title = {MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26406-26416} }

Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge
Dongjin Kim,
Sung Jin Um,
Sangmin Lee,
Jung Uk Kim
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_CVPR, author = {Kim, Dongjin and Um, Sung Jin and Lee, Sangmin and Kim, Jung Uk}, title = {Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26467-26476} }

Regressor-Segmenter Mutual Prompt Learning for Crowd Counting
Mingyue Guo,
Li Yuan,
Zhaoyi Yan,
Binghui Chen,
Yaowei Wang,
Qixiang Ye
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2024_CVPR, author = {Guo, Mingyue and Yuan, Li and Yan, Zhaoyi and Chen, Binghui and Wang, Yaowei and Ye, Qixiang}, title = {Regressor-Segmenter Mutual Prompt Learning for Crowd Counting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28380-28389} }

Instantaneous Perception of Moving Objects in 3D
Di Liu,
Bingbing Zhuang,
Dimitris N. Metaxas,
Manmohan Chandraker
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Di and Zhuang, Bingbing and Metaxas, Dimitris N. and Chandraker, Manmohan}, title = {Instantaneous Perception of Moving Objects in 3D}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19573-19583} }

CORE-MPI: Consistency Object Removal with Embedding MultiPlane Image
Donggeun Yoon,
Donghyeon Cho
[pdf] [supp]
[bibtex]
@InProceedings{Yoon_2024_CVPR, author = {Yoon, Donggeun and Cho, Donghyeon}, title = {CORE-MPI: Consistency Object Removal with Embedding MultiPlane Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20081-20090} }

Backpropagation-free Network for 3D Test-time Adaptation
Yanshuo Wang,
Ali Cheraghian,
Zeeshan Hayder,
Jie Hong,
Sameera Ramasinghe,
Shafin Rahman,
David Ahmedt-Aristizabal,
Xuesong Li,
Lars Petersson,
Mehrtash Harandi
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Yanshuo and Cheraghian, Ali and Hayder, Zeeshan and Hong, Jie and Ramasinghe, Sameera and Rahman, Shafin and Ahmedt-Aristizabal, David and Li, Xuesong and Petersson, Lars and Harandi, Mehrtash}, title = {Backpropagation-free Network for 3D Test-time Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23231-23241} }

ParamISP: Learned Forward and Inverse ISPs using Camera Parameters
Woohyeok Kim,
Geonu Kim,
Junyong Lee,
Seungyong Lee,
Seung-Hwan Baek,
Sunghyun Cho
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_CVPR, author = {Kim, Woohyeok and Kim, Geonu and Lee, Junyong and Lee, Seungyong and Baek, Seung-Hwan and Cho, Sunghyun}, title = {ParamISP: Learned Forward and Inverse ISPs using Camera Parameters}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26067-26076} }

Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models
Jingyao Xu,
Yuetong Lu,
Yandong Li,
Siyang Lu,
Dongdong Wang,
Xiang Wei
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2024_CVPR, author = {Xu, Jingyao and Lu, Yuetong and Li, Yandong and Lu, Siyang and Wang, Dongdong and Wei, Xiang}, title = {Perturbing Attention Gives You More Bang for the Buck: Subtle Imaging Perturbations That Efficiently Fool Customized Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24534-24543} }

SeNM-VAE: Semi-Supervised Noise Modeling with Hierarchical Variational Autoencoder
Dihan Zheng,
Yihang Zou,
Xiaowen Zhang,
Chenglong Bao
[pdf] [supp]
[bibtex]
@InProceedings{Zheng_2024_CVPR, author = {Zheng, Dihan and Zou, Yihang and Zhang, Xiaowen and Bao, Chenglong}, title = {SeNM-VAE: Semi-Supervised Noise Modeling with Hierarchical Variational Autoencoder}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25889-25899} }

Anchor-based Robust Finetuning of Vision-Language Models
Jinwei Han,
Zhiwen Lin,
Zhongyisun Sun,
Yingguo Gao,
Ke Yan,
Shouhong Ding,
Yuan Gao,
Gui-Song Xia
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2024_CVPR, author = {Han, Jinwei and Lin, Zhiwen and Sun, Zhongyisun and Gao, Yingguo and Yan, Ke and Ding, Shouhong and Gao, Yuan and Xia, Gui-Song}, title = {Anchor-based Robust Finetuning of Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26919-26928} }

DiSR-NeRF: Diffusion-Guided View-Consistent Super-Resolution NeRF
Jie Long Lee,
Chen Li,
Gim Hee Lee
[pdf] [supp]
[bibtex]
@InProceedings{Lee_2024_CVPR, author = {Lee, Jie Long and Li, Chen and Lee, Gim Hee}, title = {DiSR-NeRF: Diffusion-Guided View-Consistent Super-Resolution NeRF}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20561-20570} }

Dispersed Structured Light for Hyperspectral 3D Imaging
Suhyun Shin,
Seokjun Choi,
Felix Heide,
Seung-Hwan Baek
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shin_2024_CVPR, author = {Shin, Suhyun and Choi, Seokjun and Heide, Felix and Baek, Seung-Hwan}, title = {Dispersed Structured Light for Hyperspectral 3D Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24997-25006} }

GLID: Pre-training a Generalist Encoder-Decoder Vision Model
Jihao Liu,
Jinliang Zheng,
Yu Liu,
Hongsheng Li
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Jihao and Zheng, Jinliang and Liu, Yu and Li, Hongsheng}, title = {GLID: Pre-training a Generalist Encoder-Decoder Vision Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22851-22860} }

PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling
Xiaoyun Zheng,
Liwei Liao,
Xufeng Li,
Jianbo Jiao,
Rongjie Wang,
Feng Gao,
Shiqi Wang,
Ronggang Wang
[pdf] [supp]
[bibtex]
@InProceedings{Zheng_2024_CVPR, author = {Zheng, Xiaoyun and Liao, Liwei and Li, Xufeng and Jiao, Jianbo and Wang, Rongjie and Gao, Feng and Wang, Shiqi and Wang, Ronggang}, title = {PKU-DyMVHumans: A Multi-View Video Benchmark for High-Fidelity Dynamic Human Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {22530-22540} }

CausalPC: Improving the Robustness of Point Cloud Classification by Causal Effect Identification
Yuanmin Huang,
Mi Zhang,
Daizong Ding,
Erling Jiang,
Zhaoxiang Wang,
Min Yang
[pdf] [supp]
[bibtex]
@InProceedings{Huang_2024_CVPR, author = {Huang, Yuanmin and Zhang, Mi and Ding, Daizong and Jiang, Erling and Wang, Zhaoxiang and Yang, Min}, title = {CausalPC: Improving the Robustness of Point Cloud Classification by Causal Effect Identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19779-19789} }

LASA: Instance Reconstruction from Real Scans using A Large-scale Aligned Shape Annotation Dataset
Haolin Liu,
Chongjie Ye,
Yinyu Nie,
Yingfan He,
Xiaoguang Han
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Haolin and Ye, Chongjie and Nie, Yinyu and He, Yingfan and Han, Xiaoguang}, title = {LASA: Instance Reconstruction from Real Scans using A Large-scale Aligned Shape Annotation Dataset}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20454-20464} }

DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Model
Zhenghao Pan,
Haijin Zeng,
Jiezhang Cao,
Kai Zhang,
Yongyong Chen
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pan_2024_CVPR, author = {Pan, Zhenghao and Zeng, Haijin and Cao, Jiezhang and Zhang, Kai and Chen, Yongyong}, title = {DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25297-25306} }

MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models
Sanjoy Chowdhury,
Sayan Nag,
K J Joseph,
Balaji Vasan Srinivasan,
Dinesh Manocha
[pdf] [supp]
[bibtex]
@InProceedings{Chowdhury_2024_CVPR, author = {Chowdhury, Sanjoy and Nag, Sayan and Joseph, K J and Srinivasan, Balaji Vasan and Manocha, Dinesh}, title = {MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26826-26835} }

Noisy-Correspondence Learning for Text-to-Image Person Re-identification
Yang Qin,
Yingke Chen,
Dezhong Peng,
Xi Peng,
Joey Tianyi Zhou,
Peng Hu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qin_2024_CVPR, author = {Qin, Yang and Chen, Yingke and Peng, Dezhong and Peng, Xi and Zhou, Joey Tianyi and Hu, Peng}, title = {Noisy-Correspondence Learning for Text-to-Image Person Re-identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27197-27206} }

PanoRecon: Real-Time Panoptic 3D Reconstruction from Monocular Video
Dong Wu,
Zike Yan,
Hongbin Zha
[pdf] [supp]
[bibtex]
@InProceedings{Wu_2024_CVPR, author = {Wu, Dong and Yan, Zike and Zha, Hongbin}, title = {PanoRecon: Real-Time Panoptic 3D Reconstruction from Monocular Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {21507-21518} }

Towards Transferable Targeted 3D Adversarial Attack in the Physical World
Yao Huang,
Yinpeng Dong,
Shouwei Ruan,
Xiao Yang,
Hang Su,
Xingxing Wei
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2024_CVPR, author = {Huang, Yao and Dong, Yinpeng and Ruan, Shouwei and Yang, Xiao and Su, Hang and Wei, Xingxing}, title = {Towards Transferable Targeted 3D Adversarial Attack in the Physical World}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24512-24522} }

SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relighting
Hoon Kim,
Minje Jang,
Wonjun Yoon,
Jisoo Lee,
Donghyun Na,
Sanghyun Woo
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_CVPR, author = {Kim, Hoon and Jang, Minje and Yoon, Wonjun and Lee, Jisoo and Na, Donghyun and Woo, Sanghyun}, title = {SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relighting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25096-25106} }

Adapters Strike Back
Jan-Martin O. Steitz,
Stefan Roth
[pdf] [supp]
[bibtex]
@InProceedings{Steitz_2024_CVPR, author = {Steitz, Jan-Martin O. and Roth, Stefan}, title = {Adapters Strike Back}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23449-23459} }

CLIP-Driven Open-Vocabulary 3D Scene Graph Generation via Cross-Modality Contrastive Learning
Lianggangxu Chen,
Xuejiao Wang,
Jiale Lu,
Shaohui Lin,
Changbo Wang,
Gaoqi He
[pdf]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Lianggangxu and Wang, Xuejiao and Lu, Jiale and Lin, Shaohui and Wang, Changbo and He, Gaoqi}, title = {CLIP-Driven Open-Vocabulary 3D Scene Graph Generation via Cross-Modality Contrastive Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27863-27873} }

StraightPCF: Straight Point Cloud Filtering
Dasith de Silva Edirimuni,
Xuequan Lu,
Gang Li,
Lei Wei,
Antonio Robles-Kelly,
Hongdong Li
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{de_Silva_Edirimuni_2024_CVPR, author = {de Silva Edirimuni, Dasith and Lu, Xuequan and Li, Gang and Wei, Lei and Robles-Kelly, Antonio and Li, Hongdong}, title = {StraightPCF: Straight Point Cloud Filtering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20721-20730} }

Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities
AJ Piergiovanni,
Isaac Noble,
Dahun Kim,
Michael S. Ryoo,
Victor Gomes,
Anelia Angelova
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Piergiovanni_2024_CVPR, author = {Piergiovanni, AJ and Noble, Isaac and Kim, Dahun and Ryoo, Michael S. and Gomes, Victor and Angelova, Anelia}, title = {Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26804-26814} }

Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer
Yuwen Tan,
Qinhao Zhou,
Xiang Xiang,
Ke Wang,
Yuchuan Wu,
Yongbin Li
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tan_2024_CVPR, author = {Tan, Yuwen and Zhou, Qinhao and Xiang, Xiang and Wang, Ke and Wu, Yuchuan and Li, Yongbin}, title = {Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23252-23262} }

Random Entangled Tokens for Adversarially Robust Vision Transformer
Huihui Gong,
Minjing Dong,
Siqi Ma,
Seyit Camtepe,
Surya Nepal,
Chang Xu
[pdf] [supp]
[bibtex]
@InProceedings{Gong_2024_CVPR, author = {Gong, Huihui and Dong, Minjing and Ma, Siqi and Camtepe, Seyit and Nepal, Surya and Xu, Chang}, title = {Random Entangled Tokens for Adversarially Robust Vision Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24554-24563} }

L2B: Learning to Bootstrap Robust Models for Combating Label Noise
Yuyin Zhou,
Xianhang Li,
Fengze Liu,
Qingyue Wei,
Xuxi Chen,
Lequan Yu,
Cihang Xie,
Matthew P. Lungren,
Lei Xing
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2024_CVPR, author = {Zhou, Yuyin and Li, Xianhang and Liu, Fengze and Wei, Qingyue and Chen, Xuxi and Yu, Lequan and Xie, Cihang and Lungren, Matthew P. and Xing, Lei}, title = {L2B: Learning to Bootstrap Robust Models for Combating Label Noise}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23523-23533} }

Tactile-Augmented Radiance Fields
Yiming Dou,
Fengyu Yang,
Yi Liu,
Antonio Loquercio,
Andrew Owens
[pdf] [arXiv]
[bibtex]
@InProceedings{Dou_2024_CVPR, author = {Dou, Yiming and Yang, Fengyu and Liu, Yi and Loquercio, Antonio and Owens, Andrew}, title = {Tactile-Augmented Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26529-26539} }

Intensity-Robust Autofocus for Spike Camera
Changqing Su,
Zhiyuan Ye,
Yongsheng Xiao,
You Zhou,
Zhen Cheng,
Bo Xiong,
Zhaofei Yu,
Tiejun Huang
[pdf] [supp]
[bibtex]
@InProceedings{Su_2024_CVPR, author = {Su, Changqing and Ye, Zhiyuan and Xiao, Yongsheng and Zhou, You and Cheng, Zhen and Xiong, Bo and Yu, Zhaofei and Huang, Tiejun}, title = {Intensity-Robust Autofocus for Spike Camera}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25018-25027} }

COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction
Qihang Ma,
Xin Tan,
Yanyun Qu,
Lizhuang Ma,
Zhizhong Zhang,
Yuan Xie
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2024_CVPR, author = {Ma, Qihang and Tan, Xin and Qu, Yanyun and Ma, Lizhuang and Zhang, Zhizhong and Xie, Yuan}, title = {COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19936-19945} }

BANF: Band-Limited Neural Fields for Levels of Detail Reconstruction
Akhmedkhan Shabanov,
Shrisudhan Govindarajan,
Cody Reading,
Lily Goli,
Daniel Rebain,
Kwang Moo Yi,
Andrea Tagliasacchi
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shabanov_2024_CVPR, author = {Shabanov, Akhmedkhan and Govindarajan, Shrisudhan and Reading, Cody and Goli, Lily and Rebain, Daniel and Yi, Kwang Moo and Tagliasacchi, Andrea}, title = {BANF: Band-Limited Neural Fields for Levels of Detail Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20571-20580} }

Physical Property Understanding from Language-Embedded Feature Fields
Albert J. Zhai,
Yuan Shen,
Emily Y. Chen,
Gloria X. Wang,
Xinlei Wang,
Sheng Wang,
Kaiyu Guan,
Shenlong Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhai_2024_CVPR, author = {Zhai, Albert J. and Shen, Yuan and Chen, Emily Y. and Wang, Gloria X. and Wang, Xinlei and Wang, Sheng and Guan, Kaiyu and Wang, Shenlong}, title = {Physical Property Understanding from Language-Embedded Feature Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28296-28305} }

LEAD: Exploring Logit Space Evolution for Model Selection
Zixuan Hu,
Xiaotong Li,
Shixiang Tang,
Jun Liu,
Yichun Hu,
Ling-Yu Duan
[pdf] [supp]
[bibtex]
@InProceedings{Hu_2024_CVPR, author = {Hu, Zixuan and Li, Xiaotong and Tang, Shixiang and Liu, Jun and Hu, Yichun and Duan, Ling-Yu}, title = {LEAD: Exploring Logit Space Evolution for Model Selection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28664-28673} }

GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians
Shenhan Qian,
Tobias Kirschstein,
Liam Schoneveld,
Davide Davoli,
Simon Giebenhain,
Matthias Nießner
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qian_2024_CVPR, author = {Qian, Shenhan and Kirschstein, Tobias and Schoneveld, Liam and Davoli, Davide and Giebenhain, Simon and Nie{\ss}ner, Matthias}, title = {GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20299-20309} }

GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions
Junjie Wang,
Jiemin Fang,
Xiaopeng Zhang,
Lingxi Xie,
Qi Tian
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Junjie and Fang, Jiemin and Zhang, Xiaopeng and Xie, Lingxi and Tian, Qi}, title = {GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {20902-20911} }

HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation
Ce Zhang,
Simon Stepputtis,
Joseph Campbell,
Katia Sycara,
Yaqi Xie
[pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Ce and Stepputtis, Simon and Campbell, Joseph and Sycara, Katia and Xie, Yaqi}, title = {HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {28233-28243} }

Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models
Peifei Zhu,
Tsubasa Takahashi,
Hirokatsu Kataoka
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2024_CVPR, author = {Zhu, Peifei and Takahashi, Tsubasa and Kataoka, Hirokatsu}, title = {Watermark-embedded Adversarial Examples for Copyright Protection against Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {24420-24430} }

TCP:Textual-based Class-aware Prompt tuning for Visual-Language Model
Hantao Yao,
Rui Zhang,
Changsheng Xu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yao_2024_CVPR, author = {Yao, Hantao and Zhang, Rui and Xu, Changsheng}, title = {TCP:Textual-based Class-aware Prompt tuning for Visual-Language Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23438-23448} }

DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data
Hanrong Ye,
Dan Xu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ye_2024_CVPR, author = {Ye, Hanrong and Xu, Dan}, title = {DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {27960-27969} }

Spike-guided Motion Deblurring with Unknown Modal Spatiotemporal Alignment
Jiyuan Zhang,
Shiyan Chen,
Yajing Zheng,
Zhaofei Yu,
Tiejun Huang
[pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Jiyuan and Chen, Shiyan and Zheng, Yajing and Yu, Zhaofei and Huang, Tiejun}, title = {Spike-guided Motion Deblurring with Unknown Modal Spatiotemporal Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {25047-25057} }

VRP-SAM: SAM with Visual Reference Prompt
Yanpeng Sun,
Jiahui Chen,
Shan Zhang,
Xinyu Zhang,
Qiang Chen,
Gang Zhang,
Errui Ding,
Jingdong Wang,
Zechao Li
[pdf] [supp]
[bibtex]
@InProceedings{Sun_2024_CVPR, author = {Sun, Yanpeng and Chen, Jiahui and Zhang, Shan and Zhang, Xinyu and Chen, Qiang and Zhang, Gang and Ding, Errui and Wang, Jingdong and Li, Zechao}, title = {VRP-SAM: SAM with Visual Reference Prompt}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23565-23574} }

Discriminability-Driven Channel Selection for Out-of-Distribution Detection
Yue Yuan,
Rundong He,
Yicong Dong,
Zhongyi Han,
Yilong Yin
[pdf]
[bibtex]
@InProceedings{Yuan_2024_CVPR, author = {Yuan, Yue and He, Rundong and Dong, Yicong and Han, Zhongyi and Yin, Yilong}, title = {Discriminability-Driven Channel Selection for Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {26171-26180} }

Traffic Scene Parsing through the TSP6K Dataset
Peng-Tao Jiang,
Yuqi Yang,