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} }

Seeing the World through Your Eyes
Hadi Alzayer,
Kevin Zhang,
Brandon Feng,
Christopher A. Metzler,
Jia-Bin Huang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Alzayer_2024_CVPR, author = {Alzayer, Hadi and Zhang, Kevin and Feng, Brandon and Metzler, Christopher A. and Huang, Jia-Bin}, title = {Seeing the World through Your Eyes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4864-4873} }

DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery
Yixuan Zhu,
Ao Li,
Yansong Tang,
Wenliang Zhao,
Jie Zhou,
Jiwen Lu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2024_CVPR, author = {Zhu, Yixuan and Li, Ao and Tang, Yansong and Zhao, Wenliang and Zhou, Jie and Lu, Jiwen}, title = {DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1101-1110} }

Ungeneralizable Examples
Jingwen Ye,
Xinchao Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ye_2024_CVPR, author = {Ye, Jingwen and Wang, Xinchao}, title = {Ungeneralizable Examples}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {11944-11953} }

LaneCPP: Continuous 3D Lane Detection using Physical Priors
Maximilian Pittner,
Joel Janai,
Alexandru P. Condurache
[pdf] [supp]
[bibtex]
@InProceedings{Pittner_2024_CVPR, author = {Pittner, Maximilian and Janai, Joel and Condurache, Alexandru P.}, title = {LaneCPP: Continuous 3D Lane Detection using Physical Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {10639-10648} }

CityDreamer: Compositional Generative Model of Unbounded 3D Cities
Haozhe Xie,
Zhaoxi Chen,
Fangzhou Hong,
Ziwei Liu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xie_2024_CVPR, author = {Xie, Haozhe and Chen, Zhaoxi and Hong, Fangzhou and Liu, Ziwei}, title = {CityDreamer: Compositional Generative Model of Unbounded 3D Cities}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9666-9675} }

HEAL-SWIN: A Vision Transformer On The Sphere
Oscar Carlsson,
Jan E. Gerken,
Hampus Linander,
Heiner Spieß,
Fredrik Ohlsson,
Christoffer Petersson,
Daniel Persson
[pdf] [supp]
[bibtex]
@InProceedings{Carlsson_2024_CVPR, author = {Carlsson, Oscar and Gerken, Jan E. and Linander, Hampus and Spie{\ss}, Heiner and Ohlsson, Fredrik and Petersson, Christoffer and Persson, Daniel}, title = {HEAL-SWIN: A Vision Transformer On The Sphere}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6067-6077} }

3D Paintbrush: Local Stylization of 3D Shapes with Cascaded Score Distillation
Dale Decatur,
Itai Lang,
Kfir Aberman,
Rana Hanocka
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Decatur_2024_CVPR, author = {Decatur, Dale and Lang, Itai and Aberman, Kfir and Hanocka, Rana}, title = {3D Paintbrush: Local Stylization of 3D Shapes with Cascaded Score Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4473-4483} }

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} }

Guided Slot Attention for Unsupervised Video Object Segmentation
Minhyeok Lee,
Suhwan Cho,
Dogyoon Lee,
Chaewon Park,
Jungho Lee,
Sangyoun Lee
[pdf] [arXiv]
[bibtex]
@InProceedings{Lee_2024_CVPR, author = {Lee, Minhyeok and Cho, Suhwan and Lee, Dogyoon and Park, Chaewon and Lee, Jungho and Lee, Sangyoun}, title = {Guided Slot Attention for Unsupervised Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3807-3816} }

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} }

Action Detection via an Image Diffusion Process
Lin Geng Foo,
Tianjiao Li,
Hossein Rahmani,
Jun Liu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Foo_2024_CVPR, author = {Foo, Lin Geng and Li, Tianjiao and Rahmani, Hossein and Liu, Jun}, title = {Action Detection via an Image Diffusion Process}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {18351-18361} }

Programmable Motion Generation for Open-Set Motion Control Tasks
Hanchao Liu,
Xiaohang Zhan,
Shaoli Huang,
Tai-Jiang Mu,
Ying Shan
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Hanchao and Zhan, Xiaohang and Huang, Shaoli and Mu, Tai-Jiang and Shan, Ying}, title = {Programmable Motion Generation for Open-Set Motion Control Tasks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1399-1408} }

SCE-MAE: Selective Correspondence Enhancement with Masked Autoencoder for Self-Supervised Landmark Estimation
Kejia Yin,
Varshanth Rao,
Ruowei Jiang,
Xudong Liu,
Parham Aarabi,
David B. Lindell
[pdf] [supp]
[bibtex]
@InProceedings{Yin_2024_CVPR, author = {Yin, Kejia and Rao, Varshanth and Jiang, Ruowei and Liu, Xudong and Aarabi, Parham and Lindell, David B.}, title = {SCE-MAE: Selective Correspondence Enhancement with Masked Autoencoder for Self-Supervised Landmark Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1313-1322} }

LAKE-RED: Camouflaged Images Generation by Latent Background Knowledge Retrieval-Augmented Diffusion
Pancheng Zhao,
Peng Xu,
Pengda Qin,
Deng-Ping Fan,
Zhicheng Zhang,
Guoli Jia,
Bowen Zhou,
Jufeng Yang
[pdf]
[bibtex]
@InProceedings{Zhao_2024_CVPR, author = {Zhao, Pancheng and Xu, Peng and Qin, Pengda and Fan, Deng-Ping and Zhang, Zhicheng and Jia, Guoli and Zhou, Bowen and Yang, Jufeng}, title = {LAKE-RED: Camouflaged Images Generation by Latent Background Knowledge Retrieval-Augmented Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4092-4101} }

TIGER: Time-Varying Denoising Model for 3D Point Cloud Generation with Diffusion Process
Zhiyuan Ren,
Minchul Kim,
Feng Liu,
Xiaoming Liu
[pdf] [supp]
[bibtex]
@InProceedings{Ren_2024_CVPR, author = {Ren, Zhiyuan and Kim, Minchul and Liu, Feng and Liu, Xiaoming}, title = {TIGER: Time-Varying Denoising Model for 3D Point Cloud Generation with Diffusion Process}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9462-9471} }

ConTex-Human: Free-View Rendering of Human from a Single Image with Texture-Consistent Synthesis
Xiangjun Gao,
Xiaoyu Li,
Chaopeng Zhang,
Qi Zhang,
Yanpei Cao,
Ying Shan,
Long Quan
[pdf] [supp]
[bibtex]
@InProceedings{Gao_2024_CVPR, author = {Gao, Xiangjun and Li, Xiaoyu and Zhang, Chaopeng and Zhang, Qi and Cao, Yanpei and Shan, Ying and Quan, Long}, title = {ConTex-Human: Free-View Rendering of Human from a Single Image with Texture-Consistent Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {10084-10094} }

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} }

ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering
Haokai Pang,
Heming Zhu,
Adam Kortylewski,
Christian Theobalt,
Marc Habermann
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pang_2024_CVPR, author = {Pang, Haokai and Zhu, Heming and Kortylewski, Adam and Theobalt, Christian and Habermann, Marc}, title = {ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1165-1175} }

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} }

ArtAdapter: Text-to-Image Style Transfer using Multi-Level Style Encoder and Explicit Adaptation
Dar-Yen Chen,
Hamish Tennent,
Ching-Wen Hsu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Dar-Yen and Tennent, Hamish and Hsu, Ching-Wen}, title = {ArtAdapter: Text-to-Image Style Transfer using Multi-Level Style Encoder and Explicit Adaptation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8619-8628} }

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} }

Streaming Dense Video Captioning
Xingyi Zhou,
Anurag Arnab,
Shyamal Buch,
Shen Yan,
Austin Myers,
Xuehan Xiong,
Arsha Nagrani,
Cordelia Schmid
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2024_CVPR, author = {Zhou, Xingyi and Arnab, Anurag and Buch, Shyamal and Yan, Shen and Myers, Austin and Xiong, Xuehan and Nagrani, Arsha and Schmid, Cordelia}, title = {Streaming Dense Video Captioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {18243-18252} }

Rethinking Inductive Biases for Surface Normal Estimation
Gwangbin Bae,
Andrew J. Davison
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bae_2024_CVPR, author = {Bae, Gwangbin and Davison, Andrew J.}, title = {Rethinking Inductive Biases for Surface Normal Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9535-9545} }

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} }

Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity
Yuhang Chen,
Wenke Huang,
Mang Ye
[pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Yuhang and Huang, Wenke and Ye, Mang}, title = {Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {12077-12086} }

Activity-Biometrics: Person Identification from Daily Activities
Shehreen Azad,
Yogesh Singh Rawat
[pdf] [supp]
[bibtex]
@InProceedings{Azad_2024_CVPR, author = {Azad, Shehreen and Rawat, Yogesh Singh}, title = {Activity-Biometrics: Person Identification from Daily Activities}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {287-296} }

Z*: Zero-shot Style Transfer via Attention Reweighting
Yingying Deng,
Xiangyu He,
Fan Tang,
Weiming Dong
[pdf] [supp]
[bibtex]
@InProceedings{Deng_2024_CVPR, author = {Deng, Yingying and He, Xiangyu and Tang, Fan and Dong, Weiming}, title = {Z*: Zero-shot Style Transfer via Attention Reweighting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6934-6944} }

HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding
Trong-Thuan Nguyen,
Pha Nguyen,
Khoa Luu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nguyen_2024_CVPR, author = {Nguyen, Trong-Thuan and Nguyen, Pha and Luu, Khoa}, title = {HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {18384-18394} }

OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning Denoising
Haichao Zhang,
Yi Xu,
Hongsheng Lu,
Takayuki Shimizu,
Yun Fu
[pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Haichao and Xu, Yi and Lu, Hongsheng and Shimizu, Takayuki and Fu, Yun}, title = {OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {14802-14811} }

FADES: Fair Disentanglement with Sensitive Relevance
Taeuk Jang,
Xiaoqian Wang
[pdf] [supp]
[bibtex]
@InProceedings{Jang_2024_CVPR, author = {Jang, Taeuk and Wang, Xiaoqian}, title = {FADES: Fair Disentanglement with Sensitive Relevance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {12067-12076} }

Learning Continuous 3D Words for Text-to-Image Generation
Ta-Ying Cheng,
Matheus Gadelha,
Thibault Groueix,
Matthew Fisher,
Radomir Mech,
Andrew Markham,
Niki Trigoni
[pdf] [arXiv]
[bibtex]
@InProceedings{Cheng_2024_CVPR, author = {Cheng, Ta-Ying and Gadelha, Matheus and Groueix, Thibault and Fisher, Matthew and Mech, Radomir and Markham, Andrew and Trigoni, Niki}, title = {Learning Continuous 3D Words for Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6753-6762} }

MarkovGen: Structured Prediction for Efficient Text-to-Image Generation
Sadeep Jayasumana,
Daniel Glasner,
Srikumar Ramalingam,
Andreas Veit,
Ayan Chakrabarti,
Sanjiv Kumar
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jayasumana_2024_CVPR, author = {Jayasumana, Sadeep and Glasner, Daniel and Ramalingam, Srikumar and Veit, Andreas and Chakrabarti, Ayan and Kumar, Sanjiv}, title = {MarkovGen: Structured Prediction for Efficient Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9316-9325} }

Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations
Kewei Wang,
Yizheng Wu,
Jun Cen,
Zhiyu Pan,
Xingyi Li,
Zhe Wang,
Zhiguo Cao,
Guosheng Lin
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Kewei and Wu, Yizheng and Cen, Jun and Pan, Zhiyu and Li, Xingyi and Wang, Zhe and Cao, Zhiguo and Lin, Guosheng}, title = {Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {14638-14647} }

HashPoint: Accelerated Point Searching and Sampling for Neural Rendering
Jiahao Ma,
Miaomiao Liu,
David Ahmedt-Aristizabal,
Chuong Nguyen
[pdf] [supp]
[bibtex]
@InProceedings{Ma_2024_CVPR, author = {Ma, Jiahao and Liu, Miaomiao and Ahmedt-Aristizabal, David and Nguyen, Chuong}, title = {HashPoint: Accelerated Point Searching and Sampling for Neural Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4462-4472} }

MFP: Making Full Use of Probability Maps for Interactive Image Segmentation
Chaewon Lee,
Seon-Ho Lee,
Chang-Su Kim
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2024_CVPR, author = {Lee, Chaewon and Lee, Seon-Ho and Kim, Chang-Su}, title = {MFP: Making Full Use of Probability Maps for Interactive Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4051-4059} }

CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection
Mikhail Kennerley,
Jian-Gang Wang,
Bharadwaj Veeravalli,
Robby T. Tan
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kennerley_2024_CVPR, author = {Kennerley, Mikhail and Wang, Jian-Gang and Veeravalli, Bharadwaj and Tan, Robby T.}, title = {CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {16541-16550} }

StyLitGAN: Image-Based Relighting via Latent Control
Anand Bhattad,
James Soole,
D.A. Forsyth
[pdf] [supp]
[bibtex]
@InProceedings{Bhattad_2024_CVPR, author = {Bhattad, Anand and Soole, James and Forsyth, D.A.}, title = {StyLitGAN: Image-Based Relighting via Latent Control}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4231-4240} }

An Empirical Study of Scaling Law for Scene Text Recognition
Miao Rang,
Zhenni Bi,
Chuanjian Liu,
Yunhe Wang,
Kai Han
[pdf] [supp]
[bibtex]
@InProceedings{Rang_2024_CVPR, author = {Rang, Miao and Bi, Zhenni and Liu, Chuanjian and Wang, Yunhe and Han, Kai}, title = {An Empirical Study of Scaling Law for Scene Text Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {15619-15629} }

Text2Loc: 3D Point Cloud Localization from Natural Language
Yan Xia,
Letian Shi,
Zifeng Ding,
Joao F. Henriques,
Daniel Cremers
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xia_2024_CVPR, author = {Xia, Yan and Shi, Letian and Ding, Zifeng and Henriques, Joao F. and Cremers, Daniel}, title = {Text2Loc: 3D Point Cloud Localization from Natural Language}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {14958-14967} }

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} }

Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework
Vu Minh Hieu Phan,
Yutong Xie,
Yuankai Qi,
Lingqiao Liu,
Liyang Liu,
Bowen Zhang,
Zhibin Liao,
Qi Wu,
Minh-Son To,
Johan W. Verjans
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Phan_2024_CVPR, author = {Phan, Vu Minh Hieu and Xie, Yutong and Qi, Yuankai and Liu, Lingqiao and Liu, Liyang and Zhang, Bowen and Liao, Zhibin and Wu, Qi and To, Minh-Son and Verjans, Johan W.}, title = {Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Framework}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {11492-11501} }

MoMask: Generative Masked Modeling of 3D Human Motions
Chuan Guo,
Yuxuan Mu,
Muhammad Gohar Javed,
Sen Wang,
Li Cheng
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2024_CVPR, author = {Guo, Chuan and Mu, Yuxuan and Javed, Muhammad Gohar and Wang, Sen and Cheng, Li}, title = {MoMask: Generative Masked Modeling of 3D Human Motions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1900-1910} }

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} }

Fitting Flats to Flats
Gabriel Dogadov,
Ugo Finnendahl,
Marc Alexa
[pdf] [supp]
[bibtex]
@InProceedings{Dogadov_2024_CVPR, author = {Dogadov, Gabriel and Finnendahl, Ugo and Alexa, Marc}, title = {Fitting Flats to Flats}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5439-5447} }

Fusing Personal and Environmental Cues for Identification and Segmentation of First-Person Camera Wearers in Third-Person Views
Ziwei Zhao,
Yuchen Wang,
Chuhua Wang
[pdf] [supp]
[bibtex]
@InProceedings{Zhao_2024_CVPR, author = {Zhao, Ziwei and Wang, Yuchen and Wang, Chuhua}, title = {Fusing Personal and Environmental Cues for Identification and Segmentation of First-Person Camera Wearers in Third-Person Views}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {16477-16487} }

Coupled Laplacian Eigenmaps for Locally-Aware 3D Rigid Point Cloud Matching
Matteo Bastico,
Etienne Decencière,
Laurent Corté,
Yannick Tillier,
David Ryckelynck
[pdf] [supp]
[bibtex]
@InProceedings{Bastico_2024_CVPR, author = {Bastico, Matteo and Decenci\`ere, Etienne and Cort\'e, Laurent and Tillier, Yannick and Ryckelynck, David}, title = {Coupled Laplacian Eigenmaps for Locally-Aware 3D Rigid Point Cloud Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3447-3458} }

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} }

Desigen: A Pipeline for Controllable Design Template Generation
Haohan Weng,
Danqing Huang,
Yu Qiao,
Zheng Hu,
Chin-Yew Lin,
Tong Zhang,
C. L. Philip Chen
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Weng_2024_CVPR, author = {Weng, Haohan and Huang, Danqing and Qiao, Yu and Hu, Zheng and Lin, Chin-Yew and Zhang, Tong and Chen, C. L. Philip}, title = {Desigen: A Pipeline for Controllable Design Template Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {12721-12732} }

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} }

Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers
Sanghyeok Lee,
Joonmyung Choi,
Hyunwoo J. Kim
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2024_CVPR, author = {Lee, Sanghyeok and Choi, Joonmyung and Kim, Hyunwoo J.}, title = {Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {15741-15750} }

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} }

Scaling Up Video Summarization Pretraining with Large Language Models
Dawit Mureja Argaw,
Seunghyun Yoon,
Fabian Caba Heilbron,
Hanieh Deilamsalehy,
Trung Bui,
Zhaowen Wang,
Franck Dernoncourt,
Joon Son Chung
[pdf] [arXiv]
[bibtex]
@InProceedings{Argaw_2024_CVPR, author = {Argaw, Dawit Mureja and Yoon, Seunghyun and Heilbron, Fabian Caba and Deilamsalehy, Hanieh and Bui, Trung and Wang, Zhaowen and Dernoncourt, Franck and Chung, Joon Son}, title = {Scaling Up Video Summarization Pretraining with Large Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8332-8341} }

Continuous Optical Zooming: A Benchmark for Arbitrary-Scale Image Super-Resolution in Real World
Huiyuan Fu,
Fei Peng,
Xianwei Li,
Yejun Li,
Xin Wang,
Huadong Ma
[pdf]
[bibtex]
@InProceedings{Fu_2024_CVPR, author = {Fu, Huiyuan and Peng, Fei and Li, Xianwei and Li, Yejun and Wang, Xin and Ma, Huadong}, title = {Continuous Optical Zooming: A Benchmark for Arbitrary-Scale Image Super-Resolution in Real World}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3035-3044} }

Sharingan: A Transformer Architecture for Multi-Person Gaze Following
Samy Tafasca,
Anshul Gupta,
Jean-Marc Odobez
[pdf] [supp]
[bibtex]
@InProceedings{Tafasca_2024_CVPR, author = {Tafasca, Samy and Gupta, Anshul and Odobez, Jean-Marc}, title = {Sharingan: A Transformer Architecture for Multi-Person Gaze Following}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2008-2017} }

ViewFusion: Towards Multi-View Consistency via Interpolated Denoising
Xianghui Yang,
Yan Zuo,
Sameera Ramasinghe,
Loris Bazzani,
Gil Avraham,
Anton van den Hengel
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2024_CVPR, author = {Yang, Xianghui and Zuo, Yan and Ramasinghe, Sameera and Bazzani, Loris and Avraham, Gil and van den Hengel, Anton}, title = {ViewFusion: Towards Multi-View Consistency via Interpolated Denoising}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9870-9880} }

SketchINR: A First Look into Sketches as Implicit Neural Representations
Hmrishav Bandyopadhyay,
Ayan Kumar Bhunia,
Pinaki Nath Chowdhury,
Aneeshan Sain,
Tao Xiang,
Timothy Hospedales,
Yi-Zhe Song
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bandyopadhyay_2024_CVPR, author = {Bandyopadhyay, Hmrishav and Bhunia, Ayan Kumar and Chowdhury, Pinaki Nath and Sain, Aneeshan and Xiang, Tao and Hospedales, Timothy and Song, Yi-Zhe}, title = {SketchINR: A First Look into Sketches as Implicit Neural Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {12565-12574} }

Open-Vocabulary Segmentation with Semantic-Assisted Calibration
Yong Liu,
Sule Bai,
Guanbin Li,
Yitong Wang,
Yansong Tang
[pdf] [arXiv]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Yong and Bai, Sule and Li, Guanbin and Wang, Yitong and Tang, Yansong}, title = {Open-Vocabulary Segmentation with Semantic-Assisted Calibration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3491-3500} }

MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images
Junwen Huang,
Hao Yu,
Kuan-Ting Yu,
Nassir Navab,
Slobodan Ilic,
Benjamin Busam
[pdf] [supp]
[bibtex]
@InProceedings{Huang_2024_CVPR, author = {Huang, Junwen and Yu, Hao and Yu, Kuan-Ting and Navab, Nassir and Ilic, Slobodan and Busam, Benjamin}, title = {MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {10095-10105} }

Towards a Perceptual Evaluation Framework for Lighting Estimation
Justine Giroux,
Mohammad Reza Karimi Dastjerdi,
Yannick Hold-Geoffroy,
Javier Vazquez-Corral,
Jean-François Lalonde
[pdf] [arXiv]
[bibtex]
@InProceedings{Giroux_2024_CVPR, author = {Giroux, Justine and Dastjerdi, Mohammad Reza Karimi and Hold-Geoffroy, Yannick and Vazquez-Corral, Javier and Lalonde, Jean-Fran\c{c}ois}, title = {Towards a Perceptual Evaluation Framework for Lighting Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4410-4419} }

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} }

Towards High-fidelity Artistic Image Vectorization via Texture-Encapsulated Shape Parameterization
Ye Chen,
Bingbing Ni,
Jinfan Liu,
Xiaoyang Huang,
Xuanhong Chen
[pdf]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Ye and Ni, Bingbing and Liu, Jinfan and Huang, Xiaoyang and Chen, Xuanhong}, title = {Towards High-fidelity Artistic Image Vectorization via Texture-Encapsulated Shape Parameterization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {15877-15886} }

On Exact Inversion of DPM-Solvers
Seongmin Hong,
Kyeonghyun Lee,
Suh Yoon Jeon,
Hyewon Bae,
Se Young Chun
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hong_2024_CVPR, author = {Hong, Seongmin and Lee, Kyeonghyun and Jeon, Suh Yoon and Bae, Hyewon and Chun, Se Young}, title = {On Exact Inversion of DPM-Solvers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7069-7078} }

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
Yunyang Xiong,
Bala Varadarajan,
Lemeng Wu,
Xiaoyu Xiang,
Fanyi Xiao,
Chenchen Zhu,
Xiaoliang Dai,
Dilin Wang,
Fei Sun,
Forrest Iandola,
Raghuraman Krishnamoorthi,
Vikas Chandra
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiong_2024_CVPR, author = {Xiong, Yunyang and Varadarajan, Bala and Wu, Lemeng and Xiang, Xiaoyu and Xiao, Fanyi and Zhu, Chenchen and Dai, Xiaoliang and Wang, Dilin and Sun, Fei and Iandola, Forrest and Krishnamoorthi, Raghuraman and Chandra, Vikas}, title = {EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {16111-16121} }

ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles
Jiawei Zhang,
Chejian Xu,
Bo Li
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Jiawei and Xu, Chejian and Li, Bo}, title = {ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {15459-15469} }

CAMEL: CAusal Motion Enhancement Tailored for Lifting Text-driven Video Editing
Guiwei Zhang,
Tianyu Zhang,
Guanglin Niu,
Zichang Tan,
Yalong Bai,
Qing Yang
[pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Guiwei and Zhang, Tianyu and Niu, Guanglin and Tan, Zichang and Bai, Yalong and Yang, Qing}, title = {CAMEL: CAusal Motion Enhancement Tailored for Lifting Text-driven Video Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9079-9088} }

Teeth-SEG: An Efficient Instance Segmentation Framework for Orthodontic Treatment based on Multi-Scale Aggregation and Anthropic Prior Knowledge
Bo Zou,
Shaofeng Wang,
Hao Liu,
Gaoyue Sun,
Yajie Wang,
FeiFei Zuo,
Chengbin Quan,
Youjian Zhao
[pdf] [supp]
[bibtex]
@InProceedings{Zou_2024_CVPR, author = {Zou, Bo and Wang, Shaofeng and Liu, Hao and Sun, Gaoyue and Wang, Yajie and Zuo, FeiFei and Quan, Chengbin and Zhao, Youjian}, title = {Teeth-SEG: An Efficient Instance Segmentation Framework for Orthodontic Treatment based on Multi-Scale Aggregation and Anthropic Prior Knowledge}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {11601-11610} }

FocSAM: Delving Deeply into Focused Objects in Segmenting Anything
You Huang,
Zongyu Lan,
Liujuan Cao,
Xianming Lin,
Shengchuan Zhang,
Guannan Jiang,
Rongrong Ji
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2024_CVPR, author = {Huang, You and Lan, Zongyu and Cao, Liujuan and Lin, Xianming and Zhang, Shengchuan and Jiang, Guannan and Ji, Rongrong}, title = {FocSAM: Delving Deeply into Focused Objects in Segmenting Anything}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3120-3130} }

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} }

PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Models
Fei Deng,
Qifei Wang,
Wei Wei,
Tingbo Hou,
Matthias Grundmann
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Deng_2024_CVPR, author = {Deng, Fei and Wang, Qifei and Wei, Wei and Hou, Tingbo and Grundmann, Matthias}, title = {PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7423-7433} }

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} }

Bayesian Diffusion Models for 3D Shape Reconstruction
Haiyang Xu,
Yu Lei,
Zeyuan Chen,
Xiang Zhang,
Yue Zhao,
Yilin Wang,
Zhuowen Tu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2024_CVPR, author = {Xu, Haiyang and Lei, Yu and Chen, Zeyuan and Zhang, Xiang and Zhao, Yue and Wang, Yilin and Tu, Zhuowen}, title = {Bayesian Diffusion Models for 3D Shape Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {10628-10638} }

Task-Customized Mixture of Adapters for General Image Fusion
Pengfei Zhu,
Yang Sun,
Bing Cao,
Qinghua Hu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2024_CVPR, author = {Zhu, Pengfei and Sun, Yang and Cao, Bing and Hu, Qinghua}, title = {Task-Customized Mixture of Adapters for General Image Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7099-7108} }

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} }

CrossKD: Cross-Head Knowledge Distillation for Object Detection
Jiabao Wang,
Yuming Chen,
Zhaohui Zheng,
Xiang Li,
Ming-Ming Cheng,
Qibin Hou
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Jiabao and Chen, Yuming and Zheng, Zhaohui and Li, Xiang and Cheng, Ming-Ming and Hou, Qibin}, title = {CrossKD: Cross-Head Knowledge Distillation for Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {16520-16530} }

Bi-level Learning of Task-Specific Decoders for Joint Registration and One-Shot Medical Image Segmentation
Xin Fan,
Xiaolin Wang,
Jiaxin Gao,
Jia Wang,
Zhongxuan Luo,
Risheng Liu
[pdf] [supp]
[bibtex]
@InProceedings{Fan_2024_CVPR, author = {Fan, Xin and Wang, Xiaolin and Gao, Jiaxin and Wang, Jia and Luo, Zhongxuan and Liu, Risheng}, title = {Bi-level Learning of Task-Specific Decoders for Joint Registration and One-Shot Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {11726-11735} }

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} }

EscherNet: A Generative Model for Scalable View Synthesis
Xin Kong,
Shikun Liu,
Xiaoyang Lyu,
Marwan Taher,
Xiaojuan Qi,
Andrew J. Davison
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kong_2024_CVPR, author = {Kong, Xin and Liu, Shikun and Lyu, Xiaoyang and Taher, Marwan and Qi, Xiaojuan and Davison, Andrew J.}, title = {EscherNet: A Generative Model for Scalable View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9503-9513} }

MeaCap: Memory-Augmented Zero-shot Image Captioning
Zequn Zeng,
Yan Xie,
Hao Zhang,
Chiyu Chen,
Bo Chen,
Zhengjue Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zeng_2024_CVPR, author = {Zeng, Zequn and Xie, Yan and Zhang, Hao and Chen, Chiyu and Chen, Bo and Wang, Zhengjue}, title = {MeaCap: Memory-Augmented Zero-shot Image Captioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {14100-14110} }

Artist-Friendly Relightable and Animatable Neural Heads
Yingyan Xu,
Prashanth Chandran,
Sebastian Weiss,
Markus Gross,
Gaspard Zoss,
Derek Bradley
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2024_CVPR, author = {Xu, Yingyan and Chandran, Prashanth and Weiss, Sebastian and Gross, Markus and Zoss, Gaspard and Bradley, Derek}, title = {Artist-Friendly Relightable and Animatable Neural Heads}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2457-2467} }

Elite360D: Towards Efficient 360 Depth Estimation via Semantic- and Distance-Aware Bi-Projection Fusion
Hao Ai,
Lin Wang
[pdf] [supp]
[bibtex]
@InProceedings{Ai_2024_CVPR, author = {Ai, Hao and Wang, Lin}, title = {Elite360D: Towards Efficient 360 Depth Estimation via Semantic- and Distance-Aware Bi-Projection Fusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9926-9935} }

From Feature to Gaze: A Generalizable Replacement of Linear Layer for Gaze Estimation
Yiwei Bao,
Feng Lu
[pdf]
[bibtex]
@InProceedings{Bao_2024_CVPR, author = {Bao, Yiwei and Lu, Feng}, title = {From Feature to Gaze: A Generalizable Replacement of Linear Layer for Gaze Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1409-1418} }

Curriculum Point Prompting for Weakly-Supervised Referring Image Segmentation
Qiyuan Dai,
Sibei Yang
[pdf] [arXiv]
[bibtex]
@InProceedings{Dai_2024_CVPR, author = {Dai, Qiyuan and Yang, Sibei}, title = {Curriculum Point Prompting for Weakly-Supervised Referring Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {13711-13722} }

EventDance: Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognition
Xu Zheng,
Lin Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2024_CVPR, author = {Zheng, Xu and Wang, Lin}, title = {EventDance: Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {17448-17458} }

CycleINR: Cycle Implicit Neural Representation for Arbitrary-Scale Volumetric Super-Resolution of Medical Data
Wei Fang,
Yuxing Tang,
Heng Guo,
Mingze Yuan,
Tony C. W. Mok,
Ke Yan,
Jiawen Yao,
Xin Chen,
Zaiyi Liu,
Le Lu,
Ling Zhang,
Minfeng Xu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fang_2024_CVPR, author = {Fang, Wei and Tang, Yuxing and Guo, Heng and Yuan, Mingze and Mok, Tony C. W. and Yan, Ke and Yao, Jiawen and Chen, Xin and Liu, Zaiyi and Lu, Le and Zhang, Ling and Xu, Minfeng}, title = {CycleINR: Cycle Implicit Neural Representation for Arbitrary-Scale Volumetric Super-Resolution of Medical Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {11631-11641} }

Boosting Image Restoration via Priors from Pre-trained Models
Xiaogang Xu,
Shu Kong,
Tao Hu,
Zhe Liu,
Hujun Bao
[pdf] [arXiv]
[bibtex]
@InProceedings{Xu_2024_CVPR, author = {Xu, Xiaogang and Kong, Shu and Hu, Tao and Liu, Zhe and Bao, Hujun}, title = {Boosting Image Restoration via Priors from Pre-trained Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2900-2909} }

VRetouchEr: Learning Cross-frame Feature Interdependence with Imperfection Flow for Face Retouching in Videos
Wen Xue,
Le Jiang,
Lianxin Xie,
Si Wu,
Yong Xu,
Hau San Wong
[pdf] [supp]
[bibtex]
@InProceedings{Xue_2024_CVPR, author = {Xue, Wen and Jiang, Le and Xie, Lianxin and Wu, Si and Xu, Yong and Wong, Hau San}, title = {VRetouchEr: Learning Cross-frame Feature Interdependence with Imperfection Flow for Face Retouching in Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9141-9150} }

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} }

Holistic Autonomous Driving Understanding by Bird's-Eye-View Injected Multi-Modal Large Models
Xinpeng Ding,
Jianhua Han,
Hang Xu,
Xiaodan Liang,
Wei Zhang,
Xiaomeng Li
[pdf] [supp]
[bibtex]
@InProceedings{Ding_2024_CVPR, author = {Ding, Xinpeng and Han, Jianhua and Xu, Hang and Liang, Xiaodan and Zhang, Wei and Li, Xiaomeng}, title = {Holistic Autonomous Driving Understanding by Bird's-Eye-View Injected Multi-Modal Large Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {13668-13677} }

Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decoder
Jinseok Kim,
Tae-Kyun Kim
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_CVPR, author = {Kim, Jinseok and Kim, Tae-Kyun}, title = {Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decoder}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9202-9211} }

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} }

Extreme Point Supervised Instance Segmentation
Hyeonjun Lee,
Sehyun Hwang,
Suha Kwak
[pdf] [supp]
[bibtex]
@InProceedings{Lee_2024_CVPR, author = {Lee, Hyeonjun and Hwang, Sehyun and Kwak, Suha}, title = {Extreme Point Supervised Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {17212-17222} }

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} }

Cache Me if You Can: Accelerating Diffusion Models through Block Caching
Felix Wimbauer,
Bichen Wu,
Edgar Schoenfeld,
Xiaoliang Dai,
Ji Hou,
Zijian He,
Artsiom Sanakoyeu,
Peizhao Zhang,
Sam Tsai,
Jonas Kohler,
Christian Rupprecht,
Daniel Cremers,
Peter Vajda,
Jialiang Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wimbauer_2024_CVPR, author = {Wimbauer, Felix and Wu, Bichen and Schoenfeld, Edgar and Dai, Xiaoliang and Hou, Ji and He, Zijian and Sanakoyeu, Artsiom and Zhang, Peizhao and Tsai, Sam and Kohler, Jonas and Rupprecht, Christian and Cremers, Daniel and Vajda, Peter and Wang, Jialiang}, title = {Cache Me if You Can: Accelerating Diffusion Models through Block Caching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6211-6220} }

MedM2G: Unifying Medical Multi-Modal Generation via Cross-Guided Diffusion with Visual Invariant
Chenlu Zhan,
Yu Lin,
Gaoang Wang,
Hongwei Wang,
Jian Wu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhan_2024_CVPR, author = {Zhan, Chenlu and Lin, Yu and Wang, Gaoang and Wang, Hongwei and Wu, Jian}, title = {MedM2G: Unifying Medical Multi-Modal Generation via Cross-Guided Diffusion with Visual Invariant}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {11502-11512} }

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} }

Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction
Devikalyan Das,
Christopher Wewer,
Raza Yunus,
Eddy Ilg,
Jan Eric Lenssen
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Das_2024_CVPR, author = {Das, Devikalyan and Wewer, Christopher and Yunus, Raza and Ilg, Eddy and Lenssen, Jan Eric}, title = {Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {10715-10725} }

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} }

PH-Net: Semi-Supervised Breast Lesion Segmentation via Patch-wise Hardness
Siyao Jiang,
Huisi Wu,
Junyang Chen,
Qin Zhang,
Jing Qin
[pdf] [supp]
[bibtex]
@InProceedings{Jiang_2024_CVPR, author = {Jiang, Siyao and Wu, Huisi and Chen, Junyang and Zhang, Qin and Qin, Jing}, title = {PH-Net: Semi-Supervised Breast Lesion Segmentation via Patch-wise Hardness}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {11418-11427} }

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} }

ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More
Jiazhou Zhou,
Xu Zheng,
Yuanhuiyi Lyu,
Lin Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2024_CVPR, author = {Zhou, Jiazhou and Zheng, Xu and Lyu, Yuanhuiyi and Wang, Lin}, title = {ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {18633-18643} }

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} }

Improving Visual Recognition with Hyperbolical Visual Hierarchy Mapping
Hyeongjun Kwon,
Jinhyun Jang,
Jin Kim,
Kwonyoung Kim,
Kwanghoon Sohn
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kwon_2024_CVPR, author = {Kwon, Hyeongjun and Jang, Jinhyun and Kim, Jin and Kim, Kwonyoung and Sohn, Kwanghoon}, title = {Improving Visual Recognition with Hyperbolical Visual Hierarchy Mapping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {17364-17374} }

ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks
Kai Han,
Yunhe Wang,
Jianyuan Guo,
Enhua Wu
[pdf]
[bibtex]
@InProceedings{Han_2024_CVPR, author = {Han, Kai and Wang, Yunhe and Guo, Jianyuan and Wu, Enhua}, title = {ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {15751-15761} }

Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
Bingxin Ke,
Anton Obukhov,
Shengyu Huang,
Nando Metzger,
Rodrigo Caye Daudt,
Konrad Schindler
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ke_2024_CVPR, author = {Ke, Bingxin and Obukhov, Anton and Huang, Shengyu and Metzger, Nando and Daudt, Rodrigo Caye and Schindler, Konrad}, title = {Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9492-9502} }

Identifying Important Group of Pixels using Interactions
Kosuke Sumiyasu,
Kazuhiko Kawamoto,
Hiroshi Kera
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sumiyasu_2024_CVPR, author = {Sumiyasu, Kosuke and Kawamoto, Kazuhiko and Kera, Hiroshi}, title = {Identifying Important Group of Pixels using Interactions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6017-6026} }

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} }

DIOD: Self-Distillation Meets Object Discovery
Sandra Kara,
Hejer Ammar,
Julien Denize,
Florian Chabot,
Quoc-Cuong Pham
[pdf] [supp]
[bibtex]
@InProceedings{Kara_2024_CVPR, author = {Kara, Sandra and Ammar, Hejer and Denize, Julien and Chabot, Florian and Pham, Quoc-Cuong}, title = {DIOD: Self-Distillation Meets Object Discovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3975-3985} }

GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh
Jing Wen,
Xiaoming Zhao,
Zhongzheng Ren,
Alexander G. Schwing,
Shenlong Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wen_2024_CVPR, author = {Wen, Jing and Zhao, Xiaoming and Ren, Zhongzheng and Schwing, Alexander G. and Wang, Shenlong}, title = {GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2059-2069} }

Neural Redshift: Random Networks are not Random Functions
Damien Teney,
Armand Mihai Nicolicioiu,
Valentin Hartmann,
Ehsan Abbasnejad
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Teney_2024_CVPR, author = {Teney, Damien and Nicolicioiu, Armand Mihai and Hartmann, Valentin and Abbasnejad, Ehsan}, title = {Neural Redshift: Random Networks are not Random Functions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4786-4796} }

HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
Xian Liu,
Xiaohang Zhan,
Jiaxiang Tang,
Ying Shan,
Gang Zeng,
Dahua Lin,
Xihui Liu,
Ziwei Liu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Xian and Zhan, Xiaohang and Tang, Jiaxiang and Shan, Ying and Zeng, Gang and Lin, Dahua and Liu, Xihui and Liu, Ziwei}, title = {HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6646-6657} }

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} }

CosmicMan: A Text-to-Image Foundation Model for Humans
Shikai Li,
Jianglin Fu,
Kaiyuan Liu,
Wentao Wang,
Kwan-Yee Lin,
Wayne Wu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Shikai and Fu, Jianglin and Liu, Kaiyuan and Wang, Wentao and Lin, Kwan-Yee and Wu, Wayne}, title = {CosmicMan: A Text-to-Image Foundation Model for Humans}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6955-6965} }

LLMs are Good Sign Language Translators
Jia Gong,
Lin Geng Foo,
Yixuan He,
Hossein Rahmani,
Jun Liu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gong_2024_CVPR, author = {Gong, Jia and Foo, Lin Geng and He, Yixuan and Rahmani, Hossein and Liu, Jun}, title = {LLMs are Good Sign Language Translators}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {18362-18372} }

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} }

JDEC: JPEG Decoding via Enhanced Continuous Cosine Coefficients
Woo Kyoung Han,
Sunghoon Im,
Jaedeok Kim,
Kyong Hwan Jin
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2024_CVPR, author = {Han, Woo Kyoung and Im, Sunghoon and Kim, Jaedeok and Jin, Kyong Hwan}, title = {JDEC: JPEG Decoding via Enhanced Continuous Cosine Coefficients}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2784-2793} }

Revisiting the Domain Shift and Sample Uncertainty in Multi-source Active Domain Transfer
Wenqiao Zhang,
Zheqi Lv,
Hao Zhou,
Jia-Wei Liu,
Juncheng Li,
Mengze Li,
Yunfei Li,
Dongping Zhang,
Yueting Zhuang,
Siliang Tang
[pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Wenqiao and Lv, Zheqi and Zhou, Hao and Liu, Jia-Wei and Li, Juncheng and Li, Mengze and Li, Yunfei and Zhang, Dongping and Zhuang, Yueting and Tang, Siliang}, title = {Revisiting the Domain Shift and Sample Uncertainty in Multi-source Active Domain Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {16751-16761} }

Learning Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification
Zhenyu Cui,
Jiahuan Zhou,
Xun Wang,
Manyu Zhu,
Yuxin Peng
[pdf] [supp]
[bibtex]
@InProceedings{Cui_2024_CVPR, author = {Cui, Zhenyu and Zhou, Jiahuan and Wang, Xun and Zhu, Manyu and Peng, Yuxin}, title = {Learning Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {16614-16623} }

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} }

CORES: Convolutional Response-based Score for Out-of-distribution Detection
Keke Tang,
Chao Hou,
Weilong Peng,
Runnan Chen,
Peican Zhu,
Wenping Wang,
Zhihong Tian
[pdf]
[bibtex]
@InProceedings{Tang_2024_CVPR, author = {Tang, Keke and Hou, Chao and Peng, Weilong and Chen, Runnan and Zhu, Peican and Wang, Wenping and Tian, Zhihong}, title = {CORES: Convolutional Response-based Score for Out-of-distribution Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {10916-10925} }

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} }

HOI-M^3: Capture Multiple Humans and Objects Interaction within Contextual Environment
Juze Zhang,
Jingyan Zhang,
Zining Song,
Zhanhe Shi,
Chengfeng Zhao,
Ye Shi,
Jingyi Yu,
Lan Xu,
Jingya Wang
[pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Juze and Zhang, Jingyan and Song, Zining and Shi, Zhanhe and Zhao, Chengfeng and Shi, Ye and Yu, Jingyi and Xu, Lan and Wang, Jingya}, title = {HOI-M{\textasciicircum}3: Capture Multiple Humans and Objects Interaction within Contextual Environment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {516-526} }

Interactive3D: Create What You Want by Interactive 3D Generation
Shaocong Dong,
Lihe Ding,
Zhanpeng Huang,
Zibin Wang,
Tianfan Xue,
Dan Xu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dong_2024_CVPR, author = {Dong, Shaocong and Ding, Lihe and Huang, Zhanpeng and Wang, Zibin and Xue, Tianfan and Xu, Dan}, title = {Interactive3D: Create What You Want by Interactive 3D Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4999-5008} }

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} }

Accurate Spatial Gene Expression Prediction by Integrating Multi-Resolution Features
Youngmin Chung,
Ji Hun Ha,
Kyeong Chan Im,
Joo Sang Lee
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chung_2024_CVPR, author = {Chung, Youngmin and Ha, Ji Hun and Im, Kyeong Chan and Lee, Joo Sang}, title = {Accurate Spatial Gene Expression Prediction by Integrating Multi-Resolution Features}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {11591-11600} }

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} }

Behind the Veil: Enhanced Indoor 3D Scene Reconstruction with Occluded Surfaces Completion
Su Sun,
Cheng Zhao,
Yuliang Guo,
Ruoyu Wang,
Xinyu Huang,
Yingjie Victor Chen,
Liu Ren
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2024_CVPR, author = {Sun, Su and Zhao, Cheng and Guo, Yuliang and Wang, Ruoyu and Huang, Xinyu and Chen, Yingjie Victor and Ren, Liu}, title = {Behind the Veil: Enhanced Indoor 3D Scene Reconstruction with Occluded Surfaces Completion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {12744-12753} }

VideoGrounding-DINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding
Syed Talal Wasim,
Muzammal Naseer,
Salman Khan,
Ming-Hsuan Yang,
Fahad Shahbaz Khan
[pdf]
[bibtex]
@InProceedings{Wasim_2024_CVPR, author = {Wasim, Syed Talal and Naseer, Muzammal and Khan, Salman and Yang, Ming-Hsuan and Khan, Fahad Shahbaz}, title = {VideoGrounding-DINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {18909-18918} }

OmniLocalRF: Omnidirectional Local Radiance Fields from Dynamic Videos
Dongyoung Choi,
Hyeonjoong Jang,
Min H. Kim
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Choi_2024_CVPR, author = {Choi, Dongyoung and Jang, Hyeonjoong and Kim, Min H.}, title = {OmniLocalRF: Omnidirectional Local Radiance Fields from Dynamic Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6871-6880} }

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} }

Semantic Human Mesh Reconstruction with Textures
Xiaoyu Zhan,
Jianxin Yang,
Yuanqi Li,
Jie Guo,
Yanwen Guo,
Wenping Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhan_2024_CVPR, author = {Zhan, Xiaoyu and Yang, Jianxin and Li, Yuanqi and Guo, Jie and Guo, Yanwen and Wang, Wenping}, title = {Semantic Human Mesh Reconstruction with Textures}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {142-152} }

Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts
Jiayi Chen,
Benteng Ma,
Hengfei Cui,
Yong Xia
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Jiayi and Ma, Benteng and Cui, Hengfei and Xia, Yong}, title = {Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shifts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {11439-11449} }

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} }

PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image Models
Yiming Zhang,
Zhening Xing,
Yanhong Zeng,
Youqing Fang,
Kai Chen
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Yiming and Xing, Zhening and Zeng, Yanhong and Fang, Youqing and Chen, Kai}, title = {PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7747-7756} }

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} }

NeRF Analogies: Example-Based Visual Attribute Transfer for NeRFs
Michael Fischer,
Zhengqin Li,
Thu Nguyen-Phuoc,
Aljaz Bozic,
Zhao Dong,
Carl Marshall,
Tobias Ritschel
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fischer_2024_CVPR, author = {Fischer, Michael and Li, Zhengqin and Nguyen-Phuoc, Thu and Bozic, Aljaz and Dong, Zhao and Marshall, Carl and Ritschel, Tobias}, title = {NeRF Analogies: Example-Based Visual Attribute Transfer for NeRFs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4640-4650} }

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} }

ViTamin: Designing Scalable Vision Models in the Vision-Language Era
Jieneng Chen,
Qihang Yu,
Xiaohui Shen,
Alan Yuille,
Liang-Chieh Chen
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Jieneng and Yu, Qihang and Shen, Xiaohui and Yuille, Alan and Chen, Liang-Chieh}, title = {ViTamin: Designing Scalable Vision Models in the Vision-Language Era}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {12954-12966} }

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} }

Seeing the Unseen: Visual Common Sense for Semantic Placement
Ram Ramrakhya,
Aniruddha Kembhavi,
Dhruv Batra,
Zsolt Kira,
Kuo-Hao Zeng,
Luca Weihs
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ramrakhya_2024_CVPR, author = {Ramrakhya, Ram and Kembhavi, Aniruddha and Batra, Dhruv and Kira, Zsolt and Zeng, Kuo-Hao and Weihs, Luca}, title = {Seeing the Unseen: Visual Common Sense for Semantic Placement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {16273-16283} }

Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On
Xu Yang,
Changxing Ding,
Zhibin Hong,
Junhao Huang,
Jin Tao,
Xiangmin Xu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2024_CVPR, author = {Yang, Xu and Ding, Changxing and Hong, Zhibin and Huang, Junhao and Tao, Jin and Xu, Xiangmin}, title = {Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7017-7026} }

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} }

Towards Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approach
Guoqiang Liang,
Kanghao Chen,
Hangyu Li,
Yunfan Lu,
Lin Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liang_2024_CVPR, author = {Liang, Guoqiang and Chen, Kanghao and Li, Hangyu and Lu, Yunfan and Wang, Lin}, title = {Towards Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approach}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {23-33} }

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} }

LLaMA-Excitor: General Instruction Tuning via Indirect Feature Interaction
Bo Zou,
Chao Yang,
Yu Qiao,
Chengbin Quan,
Youjian Zhao
[pdf] [supp]
[bibtex]
@InProceedings{Zou_2024_CVPR, author = {Zou, Bo and Yang, Chao and Qiao, Yu and Quan, Chengbin and Zhao, Youjian}, title = {LLaMA-Excitor: General Instruction Tuning via Indirect Feature Interaction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {14089-14099} }

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} }

From a Bird's Eye View to See: Joint Camera and Subject Registration without the Camera Calibration
Zekun Qian,
Ruize Han,
Wei Feng,
Song Wang
[pdf] [supp]
[bibtex]
@InProceedings{Qian_2024_CVPR, author = {Qian, Zekun and Han, Ruize and Feng, Wei and Wang, Song}, title = {From a Bird's Eye View to See: Joint Camera and Subject Registration without the Camera Calibration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {863-873} }

Steerers: A Framework for Rotation Equivariant Keypoint Descriptors
Georg Bökman,
Johan Edstedt,
Michael Felsberg,
Fredrik Kahl
[pdf] [supp]
[bibtex]
@InProceedings{Bokman_2024_CVPR, author = {B\"okman, Georg and Edstedt, Johan and Felsberg, Michael and Kahl, Fredrik}, title = {Steerers: A Framework for Rotation Equivariant Keypoint Descriptors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4885-4895} }

Efficient Dataset Distillation via Minimax Diffusion
Jianyang Gu,
Saeed Vahidian,
Vyacheslav Kungurtsev,
Haonan Wang,
Wei Jiang,
Yang You,
Yiran Chen
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gu_2024_CVPR, author = {Gu, Jianyang and Vahidian, Saeed and Kungurtsev, Vyacheslav and Wang, Haonan and Jiang, Wei and You, Yang and Chen, Yiran}, title = {Efficient Dataset Distillation via Minimax Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {15793-15803} }

Posterior Distillation Sampling
Juil Koo,
Chanho Park,
Minhyuk Sung
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Koo_2024_CVPR, author = {Koo, Juil and Park, Chanho and Sung, Minhyuk}, title = {Posterior Distillation Sampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {13352-13361} }

HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields
Haozhe Qi,
Chen Zhao,
Mathieu Salzmann,
Alexander Mathis
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qi_2024_CVPR, author = {Qi, Haozhe and Zhao, Chen and Salzmann, Mathieu and Mathis, Alexander}, title = {HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {10392-10402} }

Enhancing Video Super-Resolution via Implicit Resampling-based Alignment
Kai Xu,
Ziwei Yu,
Xin Wang,
Michael Bi Mi,
Angela Yao
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2024_CVPR, author = {Xu, Kai and Yu, Ziwei and Wang, Xin and Mi, Michael Bi and Yao, Angela}, title = {Enhancing Video Super-Resolution via Implicit Resampling-based Alignment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2546-2555} }

DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis
Yuming Gu,
Hongyi Xu,
You Xie,
Guoxian Song,
Yichun Shi,
Di Chang,
Jing Yang,
Linjie Luo
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gu_2024_CVPR, author = {Gu, Yuming and Xu, Hongyi and Xie, You and Song, Guoxian and Shi, Yichun and Chang, Di and Yang, Jing and Luo, Linjie}, title = {DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {10456-10465} }

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} }

Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model
Zelin Peng,
Zhengqin Xu,
Zhilin Zeng,
Lingxi Xie,
Qi Tian,
Wei Shen
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Peng_2024_CVPR, author = {Peng, Zelin and Xu, Zhengqin and Zeng, Zhilin and Xie, Lingxi and Tian, Qi and Shen, Wei}, title = {Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3743-3752} }

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} }

Masked and Shuffled Blind Spot Denoising for Real-World Images
Hamadi Chihaoui,
Paolo Favaro
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chihaoui_2024_CVPR, author = {Chihaoui, Hamadi and Favaro, Paolo}, title = {Masked and Shuffled Blind Spot Denoising for Real-World Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3025-3034} }

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} }

DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatars
Tobias Kirschstein,
Simon Giebenhain,
Matthias Nießner
[pdf] [supp]
[bibtex]
@InProceedings{Kirschstein_2024_CVPR, author = {Kirschstein, Tobias and Giebenhain, Simon and Nie{\ss}ner, Matthias}, title = {DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatars}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5481-5492} }

Data-Free Quantization via Pseudo-label Filtering
Chunxiao Fan,
Ziqi Wang,
Dan Guo,
Meng Wang
[pdf]
[bibtex]
@InProceedings{Fan_2024_CVPR, author = {Fan, Chunxiao and Wang, Ziqi and Guo, Dan and Wang, Meng}, title = {Data-Free Quantization via Pseudo-label Filtering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5589-5598} }

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} }

Generative Powers of Ten
Xiaojuan Wang,
Janne Kontkanen,
Brian Curless,
Steven M. Seitz,
Ira Kemelmacher-Shlizerman,
Ben Mildenhall,
Pratul Srinivasan,
Dor Verbin,
Aleksander Holynski
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Xiaojuan and Kontkanen, Janne and Curless, Brian and Seitz, Steven M. and Kemelmacher-Shlizerman, Ira and Mildenhall, Ben and Srinivasan, Pratul and Verbin, Dor and Holynski, Aleksander}, title = {Generative Powers of Ten}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7173-7182} }

H-ViT: A Hierarchical Vision Transformer for Deformable Image Registration
Morteza Ghahremani,
Mohammad Khateri,
Bailiang Jian,
Benedikt Wiestler,
Ehsan Adeli,
Christian Wachinger
[pdf] [supp]
[bibtex]
@InProceedings{Ghahremani_2024_CVPR, author = {Ghahremani, Morteza and Khateri, Mohammad and Jian, Bailiang and Wiestler, Benedikt and Adeli, Ehsan and Wachinger, Christian}, title = {H-ViT: A Hierarchical Vision Transformer for Deformable Image Registration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {11513-11523} }

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} }

VideoLLM-online: Online Video Large Language Model for Streaming Video
Joya Chen,
Zhaoyang Lv,
Shiwei Wu,
Kevin Qinghong Lin,
Chenan Song,
Difei Gao,
Jia-Wei Liu,
Ziteng Gao,
Dongxing Mao,
Mike Zheng Shou
[pdf] [supp]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Joya and Lv, Zhaoyang and Wu, Shiwei and Lin, Kevin Qinghong and Song, Chenan and Gao, Difei and Liu, Jia-Wei and Gao, Ziteng and Mao, Dongxing and Shou, Mike Zheng}, title = {VideoLLM-online: Online Video Large Language Model for Streaming Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {18407-18418} }

Text-conditional Attribute Alignment across Latent Spaces for 3D Controllable Face Image Synthesis
Feifan Xu,
Rui Li,
Si Wu,
Yong Xu,
Hau San Wong
[pdf]
[bibtex]
@InProceedings{Xu_2024_CVPR, author = {Xu, Feifan and Li, Rui and Wu, Si and Xu, Yong and Wong, Hau San}, title = {Text-conditional Attribute Alignment across Latent Spaces for 3D Controllable Face Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9172-9181} }

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} }

Correcting Diffusion Generation through Resampling
Yujian Liu,
Yang Zhang,
Tommi Jaakkola,
Shiyu Chang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Yujian and Zhang, Yang and Jaakkola, Tommi and Chang, Shiyu}, title = {Correcting Diffusion Generation through Resampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8713-8723} }

Towards Better Vision-Inspired Vision-Language Models
Yun-Hao Cao,
Kaixiang Ji,
Ziyuan Huang,
Chuanyang Zheng,
Jiajia Liu,
Jian Wang,
Jingdong Chen,
Ming Yang
[pdf]
[bibtex]
@InProceedings{Cao_2024_CVPR, author = {Cao, Yun-Hao and Ji, Kaixiang and Huang, Ziyuan and Zheng, Chuanyang and Liu, Jiajia and Wang, Jian and Chen, Jingdong and Yang, Ming}, title = {Towards Better Vision-Inspired Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {13537-13547} }

VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object Detection
Zihua Liu,
Hiroki Sakuma,
Masatoshi Okutomi
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Zihua and Sakuma, Hiroki and Okutomi, Masatoshi}, title = {VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {17354-17363} }

RILA: Reflective and Imaginative Language Agent for Zero-Shot Semantic Audio-Visual Navigation
Zeyuan Yang,
Jiageng Liu,
Peihao Chen,
Anoop Cherian,
Tim K. Marks,
Jonathan Le Roux,
Chuang Gan
[pdf] [supp]
[bibtex]
@InProceedings{Yang_2024_CVPR, author = {Yang, Zeyuan and Liu, Jiageng and Chen, Peihao and Cherian, Anoop and Marks, Tim K. and Le Roux, Jonathan and Gan, Chuang}, title = {RILA: Reflective and Imaginative Language Agent for Zero-Shot Semantic Audio-Visual Navigation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {16251-16261} }

Endow SAM with Keen Eyes: Temporal-spatial Prompt Learning for Video Camouflaged Object Detection
Wenjun Hui,
Zhenfeng Zhu,
Shuai Zheng,
Yao Zhao
[pdf]
[bibtex]
@InProceedings{Hui_2024_CVPR, author = {Hui, Wenjun and Zhu, Zhenfeng and Zheng, Shuai and Zhao, Yao}, title = {Endow SAM with Keen Eyes: Temporal-spatial Prompt Learning for Video Camouflaged Object Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19058-19067} }

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} }

AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings
Jamie Watson,
Filippo Aleotti,
Mohamed Sayed,
Zawar Qureshi,
Oisin Mac Aodha,
Gabriel Brostow,
Michael Firman,
Sara Vicente
[pdf]
[bibtex]
@InProceedings{Watson_2024_CVPR, author = {Watson, Jamie and Aleotti, Filippo and Sayed, Mohamed and Qureshi, Zawar and Mac Aodha, Oisin and Brostow, Gabriel and Firman, Michael and Vicente, Sara}, title = {AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5270-5280} }

Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection
Huan Liu,
Zichang Tan,
Chuangchuang Tan,
Yunchao Wei,
Jingdong Wang,
Yao Zhao
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Huan and Tan, Zichang and Tan, Chuangchuang and Wei, Yunchao and Wang, Jingdong and Zhao, Yao}, title = {Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {10770-10780} }

PostureHMR: Posture Transformation for 3D Human Mesh Recovery
Yu-Pei Song,
Xiao Wu,
Zhaoquan Yuan,
Jian-Jun Qiao,
Qiang Peng
[pdf] [supp]
[bibtex]
@InProceedings{Song_2024_CVPR, author = {Song, Yu-Pei and Wu, Xiao and Yuan, Zhaoquan and Qiao, Jian-Jun and Peng, Qiang}, title = {PostureHMR: Posture Transformation for 3D Human Mesh Recovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9732-9741} }

Blur2Blur: Blur Conversion for Unsupervised Image Deblurring on Unknown Domains
Bang-Dang Pham,
Phong Tran,
Anh Tran,
Cuong Pham,
Rang Nguyen,
Minh Hoai
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pham_2024_CVPR, author = {Pham, Bang-Dang and Tran, Phong and Tran, Anh and Pham, Cuong and Nguyen, Rang and Hoai, Minh}, title = {Blur2Blur: Blur Conversion for Unsupervised Image Deblurring on Unknown Domains}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2804-2813} }

Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis
Xin Zhou,
Dingkang Liang,
Wei Xu,
Xingkui Zhu,
Yihan Xu,
Zhikang Zou,
Xiang Bai
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2024_CVPR, author = {Zhou, Xin and Liang, Dingkang and Xu, Wei and Zhu, Xingkui and Xu, Yihan and Zou, Zhikang and Bai, Xiang}, title = {Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {14707-14717} }

Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches
Qing Yu,
Mikihiro Tanaka,
Kent Fujiwara
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2024_CVPR, author = {Yu, Qing and Tanaka, Mikihiro and Fujiwara, Kent}, title = {Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {937-946} }

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} }

Wonder3D: Single Image to 3D using Cross-Domain Diffusion
Xiaoxiao Long,
Yuan-Chen Guo,
Cheng Lin,
Yuan Liu,
Zhiyang Dou,
Lingjie Liu,
Yuexin Ma,
Song-Hai Zhang,
Marc Habermann,
Christian Theobalt,
Wenping Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Long_2024_CVPR, author = {Long, Xiaoxiao and Guo, Yuan-Chen and Lin, Cheng and Liu, Yuan and Dou, Zhiyang and Liu, Lingjie and Ma, Yuexin and Zhang, Song-Hai and Habermann, Marc and Theobalt, Christian and Wang, Wenping}, title = {Wonder3D: Single Image to 3D using Cross-Domain Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9970-9980} }

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} }

Clustering for Protein Representation Learning
Ruijie Quan,
Wenguan Wang,
Fan Ma,
Hehe Fan,
Yi Yang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Quan_2024_CVPR, author = {Quan, Ruijie and Wang, Wenguan and Ma, Fan and Fan, Hehe and Yang, Yi}, title = {Clustering for Protein Representation Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {319-329} }

CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation
Boyuan Sun,
Yuqi Yang,
Le Zhang,
Ming-Ming Cheng,
Qibin Hou
[pdf] [arXiv]
[bibtex]
@InProceedings{Sun_2024_CVPR, author = {Sun, Boyuan and Yang, Yuqi and Zhang, Le and Cheng, Ming-Ming and Hou, Qibin}, title = {CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3097-3107} }

Estimating Extreme 3D Image Rotations using Cascaded Attention
Shay Dekel,
Yosi Keller,
Martin Cadik
[pdf] [supp]
[bibtex]
@InProceedings{Dekel_2024_CVPR, author = {Dekel, Shay and Keller, Yosi and Cadik, Martin}, title = {Estimating Extreme 3D Image Rotations using Cascaded Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2588-2598} }

RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D
Lingteng Qiu,
Guanying Chen,
Xiaodong Gu,
Qi Zuo,
Mutian Xu,
Yushuang Wu,
Weihao Yuan,
Zilong Dong,
Liefeng Bo,
Xiaoguang Han
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qiu_2024_CVPR, author = {Qiu, Lingteng and Chen, Guanying and Gu, Xiaodong and Zuo, Qi and Xu, Mutian and Wu, Yushuang and Yuan, Weihao and Dong, Zilong and Bo, Liefeng and Han, Xiaoguang}, title = {RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9914-9925} }

Adapt or Perish: Adaptive Sparse Transformer with Attentive Feature Refinement for Image Restoration
Shihao Zhou,
Duosheng Chen,
Jinshan Pan,
Jinglei Shi,
Jufeng Yang
[pdf]
[bibtex]
@InProceedings{Zhou_2024_CVPR, author = {Zhou, Shihao and Chen, Duosheng and Pan, Jinshan and Shi, Jinglei and Yang, Jufeng}, title = {Adapt or Perish: Adaptive Sparse Transformer with Attentive Feature Refinement for Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2952-2963} }

VINECS: Video-based Neural Character Skinning
Zhouyingcheng Liao,
Vladislav Golyanik,
Marc Habermann,
Christian Theobalt
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liao_2024_CVPR, author = {Liao, Zhouyingcheng and Golyanik, Vladislav and Habermann, Marc and Theobalt, Christian}, title = {VINECS: Video-based Neural Character Skinning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1377-1387} }

Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions
Zeyu Han,
Fangrui Zhu,
Qianru Lao,
Huaizu Jiang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Han_2024_CVPR, author = {Han, Zeyu and Zhu, Fangrui and Lao, Qianru and Jiang, Huaizu}, title = {Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {14364-14374} }

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} }

Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers
Zi-Xin Zou,
Zhipeng Yu,
Yuan-Chen Guo,
Yangguang Li,
Ding Liang,
Yan-Pei Cao,
Song-Hai Zhang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zou_2024_CVPR, author = {Zou, Zi-Xin and Yu, Zhipeng and Guo, Yuan-Chen and Li, Yangguang and Liang, Ding and Cao, Yan-Pei and Zhang, Song-Hai}, title = {Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {10324-10335} }

WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights
Youngdong Jang,
Dong In Lee,
MinHyuk Jang,
Jong Wook Kim,
Feng Yang,
Sangpil Kim
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jang_2024_CVPR, author = {Jang, Youngdong and Lee, Dong In and Jang, MinHyuk and Kim, Jong Wook and Yang, Feng and Kim, Sangpil}, title = {WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {12087-12097} }

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} }

Your Student is Better Than Expected: Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models
Nikita Starodubcev,
Dmitry Baranchuk,
Artem Fedorov,
Artem Babenko
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Starodubcev_2024_CVPR, author = {Starodubcev, Nikita and Baranchuk, Dmitry and Fedorov, Artem and Babenko, Artem}, title = {Your Student is Better Than Expected: Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9275-9285} }

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} }

SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design
Seokju Yun,
Youngmin Ro
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yun_2024_CVPR, author = {Yun, Seokju and Ro, Youngmin}, title = {SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5756-5767} }

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} }

Instance-aware Contrastive Learning for Occluded Human Mesh Reconstruction
Mi-Gyeong Gwon,
Gi-Mun Um,
Won-Sik Cheong,
Wonjun Kim
[pdf] [supp]
[bibtex]
@InProceedings{Gwon_2024_CVPR, author = {Gwon, Mi-Gyeong and Um, Gi-Mun and Cheong, Won-Sik and Kim, Wonjun}, title = {Instance-aware Contrastive Learning for Occluded Human Mesh Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {10553-10562} }

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} }

Robust Noisy Correspondence Learning with Equivariant Similarity Consistency
Yuchen Yang,
Likai Wang,
Erkun Yang,
Cheng Deng
[pdf] [supp]
[bibtex]
@InProceedings{Yang_2024_CVPR, author = {Yang, Yuchen and Wang, Likai and Yang, Erkun and Deng, Cheng}, title = {Robust Noisy Correspondence Learning with Equivariant Similarity Consistency}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {17700-17709} }

CommonCanvas: Open Diffusion Models Trained on Creative-Commons Images
Aaron Gokaslan,
A. Feder Cooper,
Jasmine Collins,
Landan Seguin,
Austin Jacobson,
Mihir Patel,
Jonathan Frankle,
Cory Stephenson,
Volodymyr Kuleshov
[pdf] [supp]
[bibtex]
@InProceedings{Gokaslan_2024_CVPR, author = {Gokaslan, Aaron and Cooper, A. Feder and Collins, Jasmine and Seguin, Landan and Jacobson, Austin and Patel, Mihir and Frankle, Jonathan and Stephenson, Cory and Kuleshov, Volodymyr}, title = {CommonCanvas: Open Diffusion Models Trained on Creative-Commons Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8250-8260} }

Prompt-Driven Referring Image Segmentation with Instance Contrasting
Chao Shang,
Zichen Song,
Heqian Qiu,
Lanxiao Wang,
Fanman Meng,
Hongliang Li
[pdf]
[bibtex]
@InProceedings{Shang_2024_CVPR, author = {Shang, Chao and Song, Zichen and Qiu, Heqian and Wang, Lanxiao and Meng, Fanman and Li, Hongliang}, title = {Prompt-Driven Referring Image Segmentation with Instance Contrasting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4124-4134} }

Image Sculpting: Precise Object Editing with 3D Geometry Control
Jiraphon Yenphraphai,
Xichen Pan,
Sainan Liu,
Daniele Panozzo,
Saining Xie
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yenphraphai_2024_CVPR, author = {Yenphraphai, Jiraphon and Pan, Xichen and Liu, Sainan and Panozzo, Daniele and Xie, Saining}, title = {Image Sculpting: Precise Object Editing with 3D Geometry Control}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4241-4251} }

Compositional Video Understanding with Spatiotemporal Structure-based Transformers
Hoyeoung Yun,
Jinwoo Ahn,
Minseo Kim,
Eun-Sol Kim
[pdf] [supp]
[bibtex]
@InProceedings{Yun_2024_CVPR, author = {Yun, Hoyeoung and Ahn, Jinwoo and Kim, Minseo and Kim, Eun-Sol}, title = {Compositional Video Understanding with Spatiotemporal Structure-based Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {18751-18760} }

3D LiDAR Mapping in Dynamic Environments using a 4D Implicit Neural Representation
Xingguang Zhong,
Yue Pan,
Cyrill Stachniss,
Jens Behley
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhong_2024_CVPR, author = {Zhong, Xingguang and Pan, Yue and Stachniss, Cyrill and Behley, Jens}, title = {3D LiDAR Mapping in Dynamic Environments using a 4D Implicit Neural Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {15417-15427} }

What When and Where? Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions
Brian Chen,
Nina Shvetsova,
Andrew Rouditchenko,
Daniel Kondermann,
Samuel Thomas,
Shih-Fu Chang,
Rogerio Feris,
James Glass,
Hilde Kuehne
[pdf] [supp]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Brian and Shvetsova, Nina and Rouditchenko, Andrew and Kondermann, Daniel and Thomas, Samuel and Chang, Shih-Fu and Feris, Rogerio and Glass, James and Kuehne, Hilde}, title = {What When and Where? Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {18419-18429} }

FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
Bowen Wen,
Wei Yang,
Jan Kautz,
Stan Birchfield
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wen_2024_CVPR, author = {Wen, Bowen and Yang, Wei and Kautz, Jan and Birchfield, Stan}, title = {FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {17868-17879} }

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} }

PFStorer: Personalized Face Restoration and Super-Resolution
Tuomas Varanka,
Tapani Toivonen,
Soumya Tripathy,
Guoying Zhao,
Erman Acar
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Varanka_2024_CVPR, author = {Varanka, Tuomas and Toivonen, Tapani and Tripathy, Soumya and Zhao, Guoying and Acar, Erman}, title = {PFStorer: Personalized Face Restoration and Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2372-2381} }

TextureDreamer: Image-Guided Texture Synthesis Through Geometry-Aware Diffusion
Yu-Ying Yeh,
Jia-Bin Huang,
Changil Kim,
Lei Xiao,
Thu Nguyen-Phuoc,
Numair Khan,
Cheng Zhang,
Manmohan Chandraker,
Carl S Marshall,
Zhao Dong,
Zhengqin Li
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yeh_2024_CVPR, author = {Yeh, Yu-Ying and Huang, Jia-Bin and Kim, Changil and Xiao, Lei and Nguyen-Phuoc, Thu and Khan, Numair and Zhang, Cheng and Chandraker, Manmohan and Marshall, Carl S and Dong, Zhao and Li, Zhengqin}, title = {TextureDreamer: Image-Guided Texture Synthesis Through Geometry-Aware Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4304-4314} }

Boosting Image Quality Assessment through Efficient Transformer Adaptation with Local Feature Enhancement
Kangmin Xu,
Liang Liao,
Jing Xiao,
Chaofeng Chen,
Haoning Wu,
Qiong Yan,
Weisi Lin
[pdf] [supp]
[bibtex]
@InProceedings{Xu_2024_CVPR, author = {Xu, Kangmin and Liao, Liang and Xiao, Jing and Chen, Chaofeng and Wu, Haoning and Yan, Qiong and Lin, Weisi}, title = {Boosting Image Quality Assessment through Efficient Transformer Adaptation with Local Feature Enhancement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2662-2672} }

Hyperbolic Anomaly Detection
Huimin Li,
Zhentao Chen,
Yunhao Xu,
Junlin Hu
[pdf]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Huimin and Chen, Zhentao and Xu, Yunhao and Hu, Junlin}, title = {Hyperbolic Anomaly Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {17511-17520} }

VLP: Vision Language Planning for Autonomous Driving
Chenbin Pan,
Burhaneddin Yaman,
Tommaso Nesti,
Abhirup Mallik,
Alessandro G Allievi,
Senem Velipasalar,
Liu Ren
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pan_2024_CVPR, author = {Pan, Chenbin and Yaman, Burhaneddin and Nesti, Tommaso and Mallik, Abhirup and Allievi, Alessandro G and Velipasalar, Senem and Ren, Liu}, title = {VLP: Vision Language Planning for Autonomous Driving}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {14760-14769} }

Attention Calibration for Disentangled Text-to-Image Personalization
Yanbing Zhang,
Mengping Yang,
Qin Zhou,
Zhe Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Yanbing and Yang, Mengping and Zhou, Qin and Wang, Zhe}, title = {Attention Calibration for Disentangled Text-to-Image Personalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4764-4774} }

ProMark: Proactive Diffusion Watermarking for Causal Attribution
Vishal Asnani,
John Collomosse,
Tu Bui,
Xiaoming Liu,
Shruti Agarwal
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Asnani_2024_CVPR, author = {Asnani, Vishal and Collomosse, John and Bui, Tu and Liu, Xiaoming and Agarwal, Shruti}, title = {ProMark: Proactive Diffusion Watermarking for Causal Attribution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {10802-10811} }

One-Shot Structure-Aware Stylized Image Synthesis
Hansam Cho,
Jonghyun Lee,
Seunggyu Chang,
Yonghyun Jeong
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cho_2024_CVPR, author = {Cho, Hansam and Lee, Jonghyun and Chang, Seunggyu and Jeong, Yonghyun}, title = {One-Shot Structure-Aware Stylized Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8302-8311} }

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} }

MR-VNet: Media Restoration using Volterra Networks
Siddharth Roheda,
Amit Unde,
Loay Rashid
[pdf]
[bibtex]
@InProceedings{Roheda_2024_CVPR, author = {Roheda, Siddharth and Unde, Amit and Rashid, Loay}, title = {MR-VNet: Media Restoration using Volterra Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6098-6107} }

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} }

Single Mesh Diffusion Models with Field Latents for Texture Generation
Thomas W. Mitchel,
Carlos Esteves,
Ameesh Makadia
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mitchel_2024_CVPR, author = {Mitchel, Thomas W. and Esteves, Carlos and Makadia, Ameesh}, title = {Single Mesh Diffusion Models with Field Latents for Texture Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7953-7963} }

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} }

Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering
Zaid Khan,
Yun Fu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Khan_2024_CVPR, author = {Khan, Zaid and Fu, Yun}, title = {Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {10854-10863} }

SAI3D: Segment Any Instance in 3D Scenes
Yingda Yin,
Yuzheng Liu,
Yang Xiao,
Daniel Cohen-Or,
Jingwei Huang,
Baoquan Chen
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yin_2024_CVPR, author = {Yin, Yingda and Liu, Yuzheng and Xiao, Yang and Cohen-Or, Daniel and Huang, Jingwei and Chen, Baoquan}, title = {SAI3D: Segment Any Instance in 3D Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3292-3302} }

Implicit Motion Function
Yue Gao,
Jiahao Li,
Lei Chu,
Yan Lu
[pdf] [supp]
[bibtex]
@InProceedings{Gao_2024_CVPR, author = {Gao, Yue and Li, Jiahao and Chu, Lei and Lu, Yan}, title = {Implicit Motion Function}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19278-19289} }

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} }

TexOct: Generating Textures of 3D Models with Octree-based Diffusion
Jialun Liu,
Chenming Wu,
Xinqi Liu,
Xing Liu,
Jinbo Wu,
Haotian Peng,
Chen Zhao,
Haocheng Feng,
Jingtuo Liu,
Errui Ding
[pdf] [supp]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Jialun and Wu, Chenming and Liu, Xinqi and Liu, Xing and Wu, Jinbo and Peng, Haotian and Zhao, Chen and Feng, Haocheng and Liu, Jingtuo and Ding, Errui}, title = {TexOct: Generating Textures of 3D Models with Octree-based Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4284-4293} }

Anatomically Constrained Implicit Face Models
Prashanth Chandran,
Gaspard Zoss
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chandran_2024_CVPR, author = {Chandran, Prashanth and Zoss, Gaspard}, title = {Anatomically Constrained Implicit Face Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2220-2229} }

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} }

Capturing Closely Interacted Two-Person Motions with Reaction Priors
Qi Fang,
Yinghui Fan,
Yanjun Li,
Junting Dong,
Dingwei Wu,
Weidong Zhang,
Kang Chen
[pdf] [supp]
[bibtex]
@InProceedings{Fang_2024_CVPR, author = {Fang, Qi and Fan, Yinghui and Li, Yanjun and Dong, Junting and Wu, Dingwei and Zhang, Weidong and Chen, Kang}, title = {Capturing Closely Interacted Two-Person Motions with Reaction Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {655-665} }

RobustSAM: Segment Anything Robustly on Degraded Images
Wei-Ting Chen,
Yu-Jiet Vong,
Sy-Yen Kuo,
Sizhou Ma,
Jian Wang
[pdf] [supp]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Wei-Ting and Vong, Yu-Jiet and Kuo, Sy-Yen and Ma, Sizhou and Wang, Jian}, title = {RobustSAM: Segment Anything Robustly on Degraded Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4081-4091} }

MultiDiff: Consistent Novel View Synthesis from a Single Image
Norman Müller,
Katja Schwarz,
Barbara Rössle,
Lorenzo Porzi,
Samuel Rota Bulò,
Matthias Nießner,
Peter Kontschieder
[pdf] [supp]
[bibtex]
@InProceedings{Muller_2024_CVPR, author = {M\"uller, Norman and Schwarz, Katja and R\"ossle, Barbara and Porzi, Lorenzo and Bul\`o, Samuel Rota and Nie{\ss}ner, Matthias and Kontschieder, Peter}, title = {MultiDiff: Consistent Novel View Synthesis from a Single Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {10258-10268} }

In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing
Yiran Xu,
Zhixin Shu,
Cameron Smith,
Seoung Wug Oh,
Jia-Bin Huang
[pdf] [supp]
[bibtex]
@InProceedings{Xu_2024_CVPR, author = {Xu, Yiran and Shu, Zhixin and Smith, Cameron and Oh, Seoung Wug and Huang, Jia-Bin}, title = {In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7225-7235} }

Atom-Level Optical Chemical Structure Recognition with Limited Supervision
Martijn Oldenhof,
Edward De Brouwer,
Adam Arany,
Yves Moreau
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Oldenhof_2024_CVPR, author = {Oldenhof, Martijn and De Brouwer, Edward and Arany, Adam and Moreau, Yves}, title = {Atom-Level Optical Chemical Structure Recognition with Limited Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {17669-17678} }

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} }

Combining Frame and GOP Embeddings for Neural Video Representation
Jens Eirik Saethre,
Roberto Azevedo,
Christopher Schroers
[pdf] [supp]
[bibtex]
@InProceedings{Saethre_2024_CVPR, author = {Saethre, Jens Eirik and Azevedo, Roberto and Schroers, Christopher}, title = {Combining Frame and GOP Embeddings for Neural Video Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9253-9263} }

LiDAR-based Person Re-identification
Wenxuan Guo,
Zhiyu Pan,
Yingping Liang,
Ziheng Xi,
Zhicheng Zhong,
Jianjiang Feng,
Jie Zhou
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2024_CVPR, author = {Guo, Wenxuan and Pan, Zhiyu and Liang, Yingping and Xi, Ziheng and Zhong, Zhicheng and Feng, Jianjiang and Zhou, Jie}, title = {LiDAR-based Person Re-identification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {17437-17447} }

Fantastic Animals and Where to Find Them: Segment Any Marine Animal with Dual SAM
Pingping Zhang,
Tianyu Yan,
Yang Liu,
Huchuan Lu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Pingping and Yan, Tianyu and Liu, Yang and Lu, Huchuan}, title = {Fantastic Animals and Where to Find Them: Segment Any Marine Animal with Dual SAM}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2578-2587} }

Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners
Yazhou Xing,
Yingqing He,
Zeyue Tian,
Xintao Wang,
Qifeng Chen
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xing_2024_CVPR, author = {Xing, Yazhou and He, Yingqing and Tian, Zeyue and Wang, Xintao and Chen, Qifeng}, title = {Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7151-7161} }

Model Adaptation for Time Constrained Embodied Control
Jaehyun Song,
Minjong Yoo,
Honguk Woo
[pdf] [supp]
[bibtex]
@InProceedings{Song_2024_CVPR, author = {Song, Jaehyun and Yoo, Minjong and Woo, Honguk}, title = {Model Adaptation for Time Constrained Embodied Control}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {16499-16508} }

Objects as Volumes: A Stochastic Geometry View of Opaque Solids
Bailey Miller,
Hanyu Chen,
Alice Lai,
Ioannis Gkioulekas
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Miller_2024_CVPR, author = {Miller, Bailey and Chen, Hanyu and Lai, Alice and Gkioulekas, Ioannis}, title = {Objects as Volumes: A Stochastic Geometry View of Opaque Solids}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {87-97} }

ActiveDC: Distribution Calibration for Active Finetuning
Wenshuai Xu,
Zhenghui Hu,
Yu Lu,
Jinzhou Meng,
Qingjie Liu,
Yunhong Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2024_CVPR, author = {Xu, Wenshuai and Hu, Zhenghui and Lu, Yu and Meng, Jinzhou and Liu, Qingjie and Wang, Yunhong}, title = {ActiveDC: Distribution Calibration for Active Finetuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {16996-17005} }

Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling
Jianan Fan,
Dongnan Liu,
Hang Chang,
Heng Huang,
Mei Chen,
Weidong Cai
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fan_2024_CVPR, author = {Fan, Jianan and Liu, Dongnan and Chang, Hang and Huang, Heng and Chen, Mei and Cai, Weidong}, title = {Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {11524-11534} }

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} }

Communication-Efficient Federated Learning with Accelerated Client Gradient
Geeho Kim,
Jinkyu Kim,
Bohyung Han
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_CVPR, author = {Kim, Geeho and Kim, Jinkyu and Han, Bohyung}, title = {Communication-Efficient Federated Learning with Accelerated Client Gradient}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {12385-12394} }

LLMs are Good Action Recognizers
Haoxuan Qu,
Yujun Cai,
Jun Liu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qu_2024_CVPR, author = {Qu, Haoxuan and Cai, Yujun and Liu, Jun}, title = {LLMs are Good Action Recognizers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {18395-18406} }

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} }

Improving Subject-Driven Image Synthesis with Subject-Agnostic Guidance
Kelvin C.K. Chan,
Yang Zhao,
Xuhui Jia,
Ming-Hsuan Yang,
Huisheng Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chan_2024_CVPR, author = {Chan, Kelvin C.K. and Zhao, Yang and Jia, Xuhui and Yang, Ming-Hsuan and Wang, Huisheng}, title = {Improving Subject-Driven Image Synthesis with Subject-Agnostic Guidance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6733-6742} }

Diffusion Model Alignment Using Direct Preference Optimization
Bram Wallace,
Meihua Dang,
Rafael Rafailov,
Linqi Zhou,
Aaron Lou,
Senthil Purushwalkam,
Stefano Ermon,
Caiming Xiong,
Shafiq Joty,
Nikhil Naik
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wallace_2024_CVPR, author = {Wallace, Bram and Dang, Meihua and Rafailov, Rafael and Zhou, Linqi and Lou, Aaron and Purushwalkam, Senthil and Ermon, Stefano and Xiong, Caiming and Joty, Shafiq and Naik, Nikhil}, title = {Diffusion Model Alignment Using Direct Preference Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8228-8238} }

Interactive Continual Learning: Fast and Slow Thinking
Biqing Qi,
Xinquan Chen,
Junqi Gao,
Dong Li,
Jianxing Liu,
Ligang Wu,
Bowen Zhou
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qi_2024_CVPR, author = {Qi, Biqing and Chen, Xinquan and Gao, Junqi and Li, Dong and Liu, Jianxing and Wu, Ligang and Zhou, Bowen}, title = {Interactive Continual Learning: Fast and Slow Thinking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {12882-12892} }

ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image
Kyle Sargent,
Zizhang Li,
Tanmay Shah,
Charles Herrmann,
Hong-Xing Yu,
Yunzhi Zhang,
Eric Ryan Chan,
Dmitry Lagun,
Li Fei-Fei,
Deqing Sun,
Jiajun Wu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sargent_2024_CVPR, author = {Sargent, Kyle and Li, Zizhang and Shah, Tanmay and Herrmann, Charles and Yu, Hong-Xing and Zhang, Yunzhi and Chan, Eric Ryan and Lagun, Dmitry and Fei-Fei, Li and Sun, Deqing and Wu, Jiajun}, title = {ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9420-9429} }

Restoration by Generation with Constrained Priors
Zheng Ding,
Xuaner Zhang,
Zhuowen Tu,
Zhihao Xia
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ding_2024_CVPR, author = {Ding, Zheng and Zhang, Xuaner and Tu, Zhuowen and Xia, Zhihao}, title = {Restoration by Generation with Constrained Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2567-2577} }

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} }

Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring
Huicong Zhang,
Haozhe Xie,
Hongxun Yao
[pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Huicong and Xie, Haozhe and Yao, Hongxun}, title = {Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2673-2681} }

Towards Learning a Generalist Model for Embodied Navigation
Duo Zheng,
Shijia Huang,
Lin Zhao,
Yiwu Zhong,
Liwei Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2024_CVPR, author = {Zheng, Duo and Huang, Shijia and Zhao, Lin and Zhong, Yiwu and Wang, Liwei}, title = {Towards Learning a Generalist Model for Embodied Navigation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {13624-13634} }

DiffusionPoser: Real-time Human Motion Reconstruction From Arbitrary Sparse Sensors Using Autoregressive Diffusion
Tom Van Wouwe,
Seunghwan Lee,
Antoine Falisse,
Scott Delp,
C. Karen Liu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Van_Wouwe_2024_CVPR, author = {Van Wouwe, Tom and Lee, Seunghwan and Falisse, Antoine and Delp, Scott and Liu, C. Karen}, title = {DiffusionPoser: Real-time Human Motion Reconstruction From Arbitrary Sparse Sensors Using Autoregressive Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2513-2523} }

MANUS: Markerless Grasp Capture using Articulated 3D Gaussians
Chandradeep Pokhariya,
Ishaan Nikhil Shah,
Angela Xing,
Zekun Li,
Kefan Chen,
Avinash Sharma,
Srinath Sridhar
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pokhariya_2024_CVPR, author = {Pokhariya, Chandradeep and Shah, Ishaan Nikhil and Xing, Angela and Li, Zekun and Chen, Kefan and Sharma, Avinash and Sridhar, Srinath}, title = {MANUS: Markerless Grasp Capture using Articulated 3D Gaussians}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2197-2208} }

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} }

BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation
Qihang Zhang,
Yinghao Xu,
Yujun Shen,
Bo Dai,
Bolei Zhou,
Ceyuan Yang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Qihang and Xu, Yinghao and Shen, Yujun and Dai, Bo and Zhou, Bolei and Yang, Ceyuan}, title = {BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6839-6849} }

3D Facial Expressions through Analysis-by-Neural-Synthesis
George Retsinas,
Panagiotis P. Filntisis,
Radek Danecek,
Victoria F. Abrevaya,
Anastasios Roussos,
Timo Bolkart,
Petros Maragos
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Retsinas_2024_CVPR, author = {Retsinas, George and Filntisis, Panagiotis P. and Danecek, Radek and Abrevaya, Victoria F. and Roussos, Anastasios and Bolkart, Timo and Maragos, Petros}, title = {3D Facial Expressions through Analysis-by-Neural-Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2490-2501} }

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} }

Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding
Zhiheng Cheng,
Qingyue Wei,
Hongru Zhu,
Yan Wang,
Liangqiong Qu,
Wei Shao,
Yuyin Zhou
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2024_CVPR, author = {Cheng, Zhiheng and Wei, Qingyue and Zhu, Hongru and Wang, Yan and Qu, Liangqiong and Shao, Wei and Zhou, Yuyin}, title = {Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3511-3522} }

Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network
Sizhe Zheng,
Pan Gao,
Peng Zhou,
Jie Qin
[pdf] [supp]
[bibtex]
@InProceedings{Zheng_2024_CVPR, author = {Zheng, Sizhe and Gao, Pan and Zhou, Peng and Qin, Jie}, title = {Puff-Net: Efficient Style Transfer with Pure Content and Style Feature Fusion Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8059-8068} }

Towards Progressive Multi-Frequency Representation for Image Warping
Jun Xiao,
Zihang Lyu,
Cong Zhang,
Yakun Ju,
Changjian Shui,
Kin-Man Lam
[pdf]
[bibtex]
@InProceedings{Xiao_2024_CVPR, author = {Xiao, Jun and Lyu, Zihang and Zhang, Cong and Ju, Yakun and Shui, Changjian and Lam, Kin-Man}, title = {Towards Progressive Multi-Frequency Representation for Image Warping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2995-3004} }

Learning to Control Camera Exposure via Reinforcement Learning
Kyunghyun Lee,
Ukcheol Shin,
Byeong-Uk Lee
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2024_CVPR, author = {Lee, Kyunghyun and Shin, Ukcheol and Lee, Byeong-Uk}, title = {Learning to Control Camera Exposure via Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2975-2983} }

Splatter Image: Ultra-Fast Single-View 3D Reconstruction
Stanislaw Szymanowicz,
Chrisitian Rupprecht,
Andrea Vedaldi
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Szymanowicz_2024_CVPR, author = {Szymanowicz, Stanislaw and Rupprecht, Chrisitian and Vedaldi, Andrea}, title = {Splatter Image: Ultra-Fast Single-View 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {10208-10217} }

Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use
Imad Eddine Toubal,
Aditya Avinash,
Neil Gordon Alldrin,
Jan Dlabal,
Wenlei Zhou,
Enming Luo,
Otilia Stretcu,
Hao Xiong,
Chun-Ta Lu,
Howard Zhou,
Ranjay Krishna,
Ariel Fuxman,
Tom Duerig
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Toubal_2024_CVPR, author = {Toubal, Imad Eddine and Avinash, Aditya and Alldrin, Neil Gordon and Dlabal, Jan and Zhou, Wenlei and Luo, Enming and Stretcu, Otilia and Xiong, Hao and Lu, Chun-Ta and Zhou, Howard and Krishna, Ranjay and Fuxman, Ariel and Duerig, Tom}, title = {Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {17553-17563} }

RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction
Baptiste Brument,
Robin Bruneau,
Yvain Quéau,
Jean Mélou,
François Bernard Lauze,
Jean-Denis Durou,
Lilian Calvet
[pdf] [supp]
[bibtex]
@InProceedings{Brument_2024_CVPR, author = {Brument, Baptiste and Bruneau, Robin and Qu\'eau, Yvain and M\'elou, Jean and Lauze, Fran\c{c}ois Bernard and Durou, Jean-Denis and Calvet, Lilian}, title = {RNb-NeuS: Reflectance and Normal-based Multi-View 3D Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5230-5239} }

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} }

GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinement
Linfang Zheng,
Tze Ho Elden Tse,
Chen Wang,
Yinghan Sun,
Hua Chen,
Ales Leonardis,
Wei Zhang,
Hyung Jin Chang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2024_CVPR, author = {Zheng, Linfang and Tse, Tze Ho Elden and Wang, Chen and Sun, Yinghan and Chen, Hua and Leonardis, Ales and Zhang, Wei and Chang, Hyung Jin}, title = {GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {10693-10703} }

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} }

Scaling Up Dynamic Human-Scene Interaction Modeling
Nan Jiang,
Zhiyuan Zhang,
Hongjie Li,
Xiaoxuan Ma,
Zan Wang,
Yixin Chen,
Tengyu Liu,
Yixin Zhu,
Siyuan Huang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2024_CVPR, author = {Jiang, Nan and Zhang, Zhiyuan and Li, Hongjie and Ma, Xiaoxuan and Wang, Zan and Chen, Yixin and Liu, Tengyu and Zhu, Yixin and Huang, Siyuan}, title = {Scaling Up Dynamic Human-Scene Interaction Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1737-1747} }

Semantic-aware SAM for Point-Prompted Instance Segmentation
Zhaoyang Wei,
Pengfei Chen,
Xuehui Yu,
Guorong Li,
Jianbin Jiao,
Zhenjun Han
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wei_2024_CVPR, author = {Wei, Zhaoyang and Chen, Pengfei and Yu, Xuehui and Li, Guorong and Jiao, Jianbin and Han, Zhenjun}, title = {Semantic-aware SAM for Point-Prompted Instance Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3585-3594} }

Learning Group Activity Features Through Person Attribute Prediction
Chihiro Nakatani,
Hiroaki Kawashima,
Norimichi Ukita
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nakatani_2024_CVPR, author = {Nakatani, Chihiro and Kawashima, Hiroaki and Ukita, Norimichi}, title = {Learning Group Activity Features Through Person Attribute Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {18233-18242} }

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} }

Plug-and-Play Diffusion Distillation
Yi-Ting Hsiao,
Siavash Khodadadeh,
Kevin Duarte,
Wei-An Lin,
Hui Qu,
Mingi Kwon,
Ratheesh Kalarot
[pdf] [supp]
[bibtex]
@InProceedings{Hsiao_2024_CVPR, author = {Hsiao, Yi-Ting and Khodadadeh, Siavash and Duarte, Kevin and Lin, Wei-An and Qu, Hui and Kwon, Mingi and Kalarot, Ratheesh}, title = {Plug-and-Play Diffusion Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {13743-13752} }

MindBridge: A Cross-Subject Brain Decoding Framework
Shizun Wang,
Songhua Liu,
Zhenxiong Tan,
Xinchao Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Shizun and Liu, Songhua and Tan, Zhenxiong and Wang, Xinchao}, title = {MindBridge: A Cross-Subject Brain Decoding Framework}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {11333-11342} }

Make Pixels Dance: High-Dynamic Video Generation
Yan Zeng,
Guoqiang Wei,
Jiani Zheng,
Jiaxin Zou,
Yang Wei,
Yuchen Zhang,
Hang Li
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zeng_2024_CVPR, author = {Zeng, Yan and Wei, Guoqiang and Zheng, Jiani and Zou, Jiaxin and Wei, Yang and Zhang, Yuchen and Li, Hang}, title = {Make Pixels Dance: High-Dynamic Video Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8850-8860} }

MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning
Chaoyi Zhang,
Kevin Lin,
Zhengyuan Yang,
Jianfeng Wang,
Linjie Li,
Chung-Ching Lin,
Zicheng Liu,
Lijuan Wang
[pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Chaoyi and Lin, Kevin and Yang, Zhengyuan and Wang, Jianfeng and Li, Linjie and Lin, Chung-Ching and Liu, Zicheng and Wang, Lijuan}, title = {MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {13647-13657} }

Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation
Xiyi Chen,
Marko Mihajlovic,
Shaofei Wang,
Sergey Prokudin,
Siyu Tang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Xiyi and Mihajlovic, Marko and Wang, Shaofei and Prokudin, Sergey and Tang, Siyu}, title = {Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {10359-10370} }

Fully Convolutional Slice-to-Volume Reconstruction for Single-Stack MRI
Sean I. Young,
Yael Balbastre,
Bruce Fischl,
Polina Golland,
Juan Eugenio Iglesias
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Young_2024_CVPR, author = {Young, Sean I. and Balbastre, Yael and Fischl, Bruce and Golland, Polina and Iglesias, Juan Eugenio}, title = {Fully Convolutional Slice-to-Volume Reconstruction for Single-Stack MRI}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {11535-11545} }

Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model
Zhicai Wang,
Longhui Wei,
Tan Wang,
Heyu Chen,
Yanbin Hao,
Xiang Wang,
Xiangnan He,
Qi Tian
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Zhicai and Wei, Longhui and Wang, Tan and Chen, Heyu and Hao, Yanbin and Wang, Xiang and He, Xiangnan and Tian, Qi}, title = {Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {17223-17233} }

A&B BNN: Add&Bit-Operation-Only Hardware-Friendly Binary Neural Network
Ruichen Ma,
Guanchao Qiao,
Yian Liu,
Liwei Meng,
Ning Ning,
Yang Liu,
Shaogang Hu
[pdf]
[bibtex]
@InProceedings{Ma_2024_CVPR, author = {Ma, Ruichen and Qiao, Guanchao and Liu, Yian and Meng, Liwei and Ning, Ning and Liu, Yang and Hu, Shaogang}, title = {A\&B BNN: Add\&Bit-Operation-Only Hardware-Friendly Binary Neural Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5704-5713} }

Alpha-CLIP: A CLIP Model Focusing on Wherever You Want
Zeyi Sun,
Ye Fang,
Tong Wu,
Pan Zhang,
Yuhang Zang,
Shu Kong,
Yuanjun Xiong,
Dahua Lin,
Jiaqi Wang
[pdf] [supp]
[bibtex]
@InProceedings{Sun_2024_CVPR, author = {Sun, Zeyi and Fang, Ye and Wu, Tong and Zhang, Pan and Zang, Yuhang and Kong, Shu and Xiong, Yuanjun and Lin, Dahua and Wang, Jiaqi}, title = {Alpha-CLIP: A CLIP Model Focusing on Wherever You Want}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {13019-13029} }

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} }

Task-aligned Part-aware Panoptic Segmentation through Joint Object-Part Representations
Daan de Geus,
Gijs Dubbelman
[pdf] [supp]
[bibtex]
@InProceedings{de_Geus_2024_CVPR, author = {de Geus, Daan and Dubbelman, Gijs}, title = {Task-aligned Part-aware Panoptic Segmentation through Joint Object-Part Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3174-3183} }

From Activation to Initialization: Scaling Insights for Optimizing Neural Fields
Hemanth Saratchandran,
Sameera Ramasinghe,
Simon Lucey
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Saratchandran_2024_CVPR, author = {Saratchandran, Hemanth and Ramasinghe, Sameera and Lucey, Simon}, title = {From Activation to Initialization: Scaling Insights for Optimizing Neural Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {413-422} }

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} }

DiffAvatar: Simulation-Ready Garment Optimization with Differentiable Simulation
Yifei Li,
Hsiao-yu Chen,
Egor Larionov,
Nikolaos Sarafianos,
Wojciech Matusik,
Tuur Stuyck
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Yifei and Chen, Hsiao-yu and Larionov, Egor and Sarafianos, Nikolaos and Matusik, Wojciech and Stuyck, Tuur}, title = {DiffAvatar: Simulation-Ready Garment Optimization with Differentiable Simulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4368-4378} }

AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning
Duojun Huang,
Xinyu Xiong,
Jie Ma,
Jichang Li,
Zequn Jie,
Lin Ma,
Guanbin Li
[pdf] [supp]
[bibtex]
@InProceedings{Huang_2024_CVPR, author = {Huang, Duojun and Xiong, Xinyu and Ma, Jie and Li, Jichang and Jie, Zequn and Ma, Lin and Li, Guanbin}, title = {AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3205-3215} }

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} }

Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolution
Zhikai Chen,
Fuchen Long,
Zhaofan Qiu,
Ting Yao,
Wengang Zhou,
Jiebo Luo,
Tao Mei
[pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Zhikai and Long, Fuchen and Qiu, Zhaofan and Yao, Ting and Zhou, Wengang and Luo, Jiebo and Mei, Tao}, title = {Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9232-9241} }

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} }

Denoising Point Clouds in Latent Space via Graph Convolution and Invertible Neural Network
Aihua Mao,
Biao Yan,
Zijing Ma,
Ying He
[pdf] [supp]
[bibtex]
@InProceedings{Mao_2024_CVPR, author = {Mao, Aihua and Yan, Biao and Ma, Zijing and He, Ying}, title = {Denoising Point Clouds in Latent Space via Graph Convolution and Invertible Neural Network}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5768-5777} }

ADA-Track: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association
Shuxiao Ding,
Lukas Schneider,
Marius Cordts,
Juergen Gall
[pdf] [supp]
[bibtex]
@InProceedings{Ding_2024_CVPR, author = {Ding, Shuxiao and Schneider, Lukas and Cordts, Marius and Gall, Juergen}, title = {ADA-Track: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {15184-15194} }

HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models
Li Pang,
Xiangyu Rui,
Long Cui,
Hongzhong Wang,
Deyu Meng,
Xiangyong Cao
[pdf] [supp]
[bibtex]
@InProceedings{Pang_2024_CVPR, author = {Pang, Li and Rui, Xiangyu and Cui, Long and Wang, Hongzhong and Meng, Deyu and Cao, Xiangyong}, title = {HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3005-3014} }

Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation
Lior Talker,
Aviad Cohen,
Erez Yosef,
Alexandra Dana,
Michael Dinerstein
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Talker_2024_CVPR, author = {Talker, Lior and Cohen, Aviad and Yosef, Erez and Dana, Alexandra and Dinerstein, Michael}, title = {Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {10606-10616} }

Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models
Hongjie Wang,
Difan Liu,
Yan Kang,
Yijun Li,
Zhe Lin,
Niraj K. Jha,
Yuchen Liu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Hongjie and Liu, Difan and Kang, Yan and Li, Yijun and Lin, Zhe and Jha, Niraj K. and Liu, Yuchen}, title = {Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {16080-16089} }

CPR: Retrieval Augmented Generation for Copyright Protection
Aditya Golatkar,
Alessandro Achille,
Luca Zancato,
Yu-Xiang Wang,
Ashwin Swaminathan,
Stefano Soatto
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Golatkar_2024_CVPR, author = {Golatkar, Aditya and Achille, Alessandro and Zancato, Luca and Wang, Yu-Xiang and Swaminathan, Ashwin and Soatto, Stefano}, title = {CPR: Retrieval Augmented Generation for Copyright Protection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {12374-12384} }

FreeDrag: Feature Dragging for Reliable Point-based Image Editing
Pengyang Ling,
Lin Chen,
Pan Zhang,
Huaian Chen,
Yi Jin,
Jinjin Zheng
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ling_2024_CVPR, author = {Ling, Pengyang and Chen, Lin and Zhang, Pan and Chen, Huaian and Jin, Yi and Zheng, Jinjin}, title = {FreeDrag: Feature Dragging for Reliable Point-based Image Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6860-6870} }

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} }

Vision-and-Language Navigation via Causal Learning
Liuyi Wang,
Zongtao He,
Ronghao Dang,
Mengjiao Shen,
Chengju Liu,
Qijun Chen
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Liuyi and He, Zongtao and Dang, Ronghao and Shen, Mengjiao and Liu, Chengju and Chen, Qijun}, title = {Vision-and-Language Navigation via Causal Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {13139-13150} }

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} }

Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)
Tsu-Ching Hsiao,
Hao-Wei Chen,
Hsuan-Kung Yang,
Chun-Yi Lee
[pdf] [arXiv]
[bibtex]
@InProceedings{Hsiao_2024_CVPR, author = {Hsiao, Tsu-Ching and Chen, Hao-Wei and Yang, Hsuan-Kung and Lee, Chun-Yi}, title = {Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {352-362} }

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} }

Unveiling Parts Beyond Objects: Towards Finer-Granularity Referring Expression Segmentation
Wenxuan Wang,
Tongtian Yue,
Yisi Zhang,
Longteng Guo,
Xingjian He,
Xinlong Wang,
Jing Liu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Wenxuan and Yue, Tongtian and Zhang, Yisi and Guo, Longteng and He, Xingjian and Wang, Xinlong and Liu, Jing}, title = {Unveiling Parts Beyond Objects: Towards Finer-Granularity Referring Expression Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {12998-13008} }

DiffInDScene: Diffusion-based High-Quality 3D Indoor Scene Generation
Xiaoliang Ju,
Zhaoyang Huang,
Yijin Li,
Guofeng Zhang,
Yu Qiao,
Hongsheng Li
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ju_2024_CVPR, author = {Ju, Xiaoliang and Huang, Zhaoyang and Li, Yijin and Zhang, Guofeng and Qiao, Yu and Li, Hongsheng}, title = {DiffInDScene: Diffusion-based High-Quality 3D Indoor Scene Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4526-4535} }

MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling
Xuzhe Zhang,
Yuhao Wu,
Elsa Angelini,
Ang Li,
Jia Guo,
Jerod M. Rasmussen,
Thomas G. O'Connor,
Pathik D. Wadhwa,
Andrea Parolin Jackowski,
Hai Li,
Jonathan Posner,
Andrew F. Laine,
Yun Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Xuzhe and Wu, Yuhao and Angelini, Elsa and Li, Ang and Guo, Jia and Rasmussen, Jerod M. and O'Connor, Thomas G. and Wadhwa, Pathik D. and Jackowski, Andrea Parolin and Li, Hai and Posner, Jonathan and Laine, Andrew F. and Wang, Yun}, title = {MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5851-5862} }

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} }

DaReNeRF: Direction-aware Representation for Dynamic Scenes
Ange Lou,
Benjamin Planche,
Zhongpai Gao,
Yamin Li,
Tianyu Luan,
Hao Ding,
Terrence Chen,
Jack Noble,
Ziyan Wu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lou_2024_CVPR, author = {Lou, Ange and Planche, Benjamin and Gao, Zhongpai and Li, Yamin and Luan, Tianyu and Ding, Hao and Chen, Terrence and Noble, Jack and Wu, Ziyan}, title = {DaReNeRF: Direction-aware Representation for Dynamic Scenes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5031-5042} }

SfmCAD: Unsupervised CAD Reconstruction by Learning Sketch-based Feature Modeling Operations
Pu Li,
Jianwei Guo,
Huibin Li,
Bedrich Benes,
Dong-Ming Yan
[pdf] [supp]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Pu and Guo, Jianwei and Li, Huibin and Benes, Bedrich and Yan, Dong-Ming}, title = {SfmCAD: Unsupervised CAD Reconstruction by Learning Sketch-based Feature Modeling Operations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4671-4680} }

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} }

Differentiable Display Photometric Stereo
Seokjun Choi,
Seungwoo Yoon,
Giljoo Nam,
Seungyong Lee,
Seung-Hwan Baek
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Choi_2024_CVPR, author = {Choi, Seokjun and Yoon, Seungwoo and Nam, Giljoo and Lee, Seungyong and Baek, Seung-Hwan}, title = {Differentiable Display Photometric Stereo}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {11831-11840} }

In-distribution Public Data Synthesis with Diffusion Models for Differentially Private Image Classification
Jinseong Park,
Yujin Choi,
Jaewook Lee
[pdf] [supp]
[bibtex]
@InProceedings{Park_2024_CVPR, author = {Park, Jinseong and Choi, Yujin and Lee, Jaewook}, title = {In-distribution Public Data Synthesis with Diffusion Models for Differentially Private Image Classification}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {12236-12246} }

Learning Degradation-unaware Representation with Prior-based Latent Transformations for Blind Face Restoration
Lianxin Xie,
Csbingbing Zheng,
Wen Xue,
Le Jiang,
Cheng Liu,
Si Wu,
Hau San Wong
[pdf]
[bibtex]
@InProceedings{Xie_2024_CVPR, author = {Xie, Lianxin and Zheng, Csbingbing and Xue, Wen and Jiang, Le and Liu, Cheng and Wu, Si and Wong, Hau San}, title = {Learning Degradation-unaware Representation with Prior-based Latent Transformations for Blind Face Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9120-9129} }

LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels
Tuo Feng,
Wenguan Wang,
Fan Ma,
Yi Yang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Feng_2024_CVPR, author = {Feng, Tuo and Wang, Wenguan and Ma, Fan and Yang, Yi}, title = {LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {14916-14927} }

Faces that Speak: Jointly Synthesising Talking Face and Speech from Text
Youngjoon Jang,
Ji-Hoon Kim,
Junseok Ahn,
Doyeop Kwak,
Hong-Sun Yang,
Yoon-Cheol Ju,
Il-Hwan Kim,
Byeong-Yeol Kim,
Joon Son Chung
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jang_2024_CVPR, author = {Jang, Youngjoon and Kim, Ji-Hoon and Ahn, Junseok and Kwak, Doyeop and Yang, Hong-Sun and Ju, Yoon-Cheol and Kim, Il-Hwan and Kim, Byeong-Yeol and Chung, Joon Son}, title = {Faces that Speak: Jointly Synthesising Talking Face and Speech from Text}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8818-8828} }

Diversified and Personalized Multi-rater Medical Image Segmentation
Yicheng Wu,
Xiangde Luo,
Zhe Xu,
Xiaoqing Guo,
Lie Ju,
Zongyuan Ge,
Wenjun Liao,
Jianfei Cai
[pdf] [arXiv]
[bibtex]
@InProceedings{Wu_2024_CVPR, author = {Wu, Yicheng and Luo, Xiangde and Xu, Zhe and Guo, Xiaoqing and Ju, Lie and Ge, Zongyuan and Liao, Wenjun and Cai, Jianfei}, title = {Diversified and Personalized Multi-rater Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {11470-11479} }

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} }

Discover and Mitigate Multiple Biased Subgroups in Image Classifiers
Zeliang Zhang,
Mingqian Feng,
Zhiheng Li,
Chenliang Xu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Zeliang and Feng, Mingqian and Li, Zhiheng and Xu, Chenliang}, title = {Discover and Mitigate Multiple Biased Subgroups in Image Classifiers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {10906-10915} }

DiffusionRegPose: Enhancing Multi-Person Pose Estimation using a Diffusion-Based End-to-End Regression Approach
Dayi Tan,
Hansheng Chen,
Wei Tian,
Lu Xiong
[pdf] [supp]
[bibtex]
@InProceedings{Tan_2024_CVPR, author = {Tan, Dayi and Chen, Hansheng and Tian, Wei and Xiong, Lu}, title = {DiffusionRegPose: Enhancing Multi-Person Pose Estimation using a Diffusion-Based End-to-End Regression Approach}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2230-2239} }

Memory-Scalable and Simplified Functional Map Learning
Robin Magnet,
Maks Ovsjanikov
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Magnet_2024_CVPR, author = {Magnet, Robin and Ovsjanikov, Maks}, title = {Memory-Scalable and Simplified Functional Map Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4041-4050} }

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} }

ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations
Rwiddhi Chakraborty,
Adrian Sletten,
Michael C. Kampffmeyer
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chakraborty_2024_CVPR, author = {Chakraborty, Rwiddhi and Sletten, Adrian and Kampffmeyer, Michael C.}, title = {ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {12017-12026} }

Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians
Yuelang Xu,
Benwang Chen,
Zhe Li,
Hongwen Zhang,
Lizhen Wang,
Zerong Zheng,
Yebin Liu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2024_CVPR, author = {Xu, Yuelang and Chen, Benwang and Li, Zhe and Zhang, Hongwen and Wang, Lizhen and Zheng, Zerong and Liu, Yebin}, title = {Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1931-1941} }

Stratified Avatar Generation from Sparse Observations
Han Feng,
Wenchao Ma,
Quankai Gao,
Xianwei Zheng,
Nan Xue,
Huijuan Xu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Feng_2024_CVPR, author = {Feng, Han and Ma, Wenchao and Gao, Quankai and Zheng, Xianwei and Xue, Nan and Xu, Huijuan}, title = {Stratified Avatar Generation from Sparse Observations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {153-163} }

Learning to Segment Referred Objects from Narrated Egocentric Videos
Yuhan Shen,
Huiyu Wang,
Xitong Yang,
Matt Feiszli,
Ehsan Elhamifar,
Lorenzo Torresani,
Effrosyni Mavroudi
[pdf] [supp]
[bibtex]
@InProceedings{Shen_2024_CVPR, author = {Shen, Yuhan and Wang, Huiyu and Yang, Xitong and Feiszli, Matt and Elhamifar, Ehsan and Torresani, Lorenzo and Mavroudi, Effrosyni}, title = {Learning to Segment Referred Objects from Narrated Egocentric Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {14510-14520} }

Rewrite the Stars
Xu Ma,
Xiyang Dai,
Yue Bai,
Yizhou Wang,
Yun Fu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2024_CVPR, author = {Ma, Xu and Dai, Xiyang and Bai, Yue and Wang, Yizhou and Fu, Yun}, title = {Rewrite the Stars}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5694-5703} }

Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images
Chaoqin Huang,
Aofan Jiang,
Jinghao Feng,
Ya Zhang,
Xinchao Wang,
Yanfeng Wang
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2024_CVPR, author = {Huang, Chaoqin and Jiang, Aofan and Feng, Jinghao and Zhang, Ya and Wang, Xinchao and Wang, Yanfeng}, title = {Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {11375-11385} }

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} }

Depth-aware Test-Time Training for Zero-shot Video Object Segmentation
Weihuang Liu,
Xi Shen,
Haolun Li,
Xiuli Bi,
Bo Liu,
Chi-Man Pun,
Xiaodong Cun
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Weihuang and Shen, Xi and Li, Haolun and Bi, Xiuli and Liu, Bo and Pun, Chi-Man and Cun, Xiaodong}, title = {Depth-aware Test-Time Training for Zero-shot Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {19218-19227} }

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} }

RMem: Restricted Memory Banks Improve Video Object Segmentation
Junbao Zhou,
Ziqi Pang,
Yu-Xiong Wang
[pdf] [supp]
[bibtex]
@InProceedings{Zhou_2024_CVPR, author = {Zhou, Junbao and Pang, Ziqi and Wang, Yu-Xiong}, title = {RMem: Restricted Memory Banks Improve Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {18602-18611} }

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} }

PairDETR : Joint Detection and Association of Human Bodies and Faces
Ammar Ali,
Georgii Gaikov,
Denis Rybalchenko,
Alexander Chigorin,
Ivan Laptev,
Sergey Zagoruyko
[pdf] [supp]
[bibtex]
@InProceedings{Ali_2024_CVPR, author = {Ali, Ammar and Gaikov, Georgii and Rybalchenko, Denis and Chigorin, Alexander and Laptev, Ivan and Zagoruyko, Sergey}, title = {PairDETR : Joint Detection and Association of Human Bodies and Faces}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {423-432} }

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} }

Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction
Junuk Cha,
Jihyeon Kim,
Jae Shin Yoon,
Seungryul Baek
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cha_2024_CVPR, author = {Cha, Junuk and Kim, Jihyeon and Yoon, Jae Shin and Baek, Seungryul}, title = {Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interaction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1577-1585} }

Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers
Hongjie Wang,
Bhishma Dedhia,
Niraj K. Jha
[pdf] [supp]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Hongjie and Dedhia, Bhishma and Jha, Niraj K.}, title = {Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {16070-16079} }

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} }

MACE: Mass Concept Erasure in Diffusion Models
Shilin Lu,
Zilan Wang,
Leyang Li,
Yanzhu Liu,
Adams Wai-Kin Kong
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2024_CVPR, author = {Lu, Shilin and Wang, Zilan and Li, Leyang and Liu, Yanzhu and Kong, Adams Wai-Kin}, title = {MACE: Mass Concept Erasure in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6430-6440} }

DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement
Hao Wu,
Huabin Liu,
Yu Qiao,
Xiao Sun
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2024_CVPR, author = {Wu, Hao and Liu, Huabin and Qiao, Yu and Sun, Xiao}, title = {DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {18699-18708} }

PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution