CVPR 2024 Open Access Repository

Papers

Back
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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] [arXiv]
[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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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] [arXiv]
[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} }
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} }
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} }
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} }
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} }
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} }
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} }
Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring: Huicong Zhang,

Haozhe Xie,

Hongxun Yao; [pdf] [supp] [arXiv]
[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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
Task-aligned Part-aware Panoptic Segmentation through Joint Object-Part Representations: Daan de Geus,

Gijs Dubbelman; [pdf] [supp] [arXiv]
[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} }
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] [arXiv]
[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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
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} }
SportsSloMo: A New Benchmark and Baselines for Human-centric Video Frame Interpolation: Jiaben Chen,

Huaizu Jiang; [pdf] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Jiaben and Jiang, Huaizu}, title = {SportsSloMo: A New Benchmark and Baselines for Human-centric Video Frame Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6475-6486} }
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} }
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} }
PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution: Honghao Chen,

Xiangxiang Chu,

Yongjian Ren,

Xin Zhao,

Kaiqi Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Honghao and Chu, Xiangxiang and Ren, Yongjian and Zhao, Xin and Huang, Kaiqi}, title = {PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5557-5567} }
AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation: Qingping Sun,

Yanjun Wang,

Ailing Zeng,

Wanqi Yin,

Chen Wei,

Wenjia Wang,

Haiyi Mei,

Chi-Sing Leung,

Ziwei Liu,

Lei Yang,

Zhongang Cai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2024_CVPR, author = {Sun, Qingping and Wang, Yanjun and Zeng, Ailing and Yin, Wanqi and Wei, Chen and Wang, Wenjia and Mei, Haiyi and Leung, Chi-Sing and Liu, Ziwei and Yang, Lei and Cai, Zhongang}, title = {AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1834-1843} }
Design2Cloth: 3D Cloth Generation from 2D Masks: Jiali Zheng,

Rolandos Alexandros Potamias,

Stefanos Zafeiriou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2024_CVPR, author = {Zheng, Jiali and Potamias, Rolandos Alexandros and Zafeiriou, Stefanos}, title = {Design2Cloth: 3D Cloth Generation from 2D Masks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1748-1758} }
Amodal Completion via Progressive Mixed Context Diffusion: Katherine Xu,

Lingzhi Zhang,

Jianbo Shi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2024_CVPR, author = {Xu, Katherine and Zhang, Lingzhi and Shi, Jianbo}, title = {Amodal Completion via Progressive Mixed Context Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9099-9109} }
Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features: Niladri Shekhar Dutt,

Sanjeev Muralikrishnan,

Niloy J. Mitra; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dutt_2024_CVPR, author = {Dutt, Niladri Shekhar and Muralikrishnan, Sanjeev and Mitra, Niloy J.}, title = {Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4494-4504} }
Cinematic Behavior Transfer via NeRF-based Differentiable Filming: Xuekun Jiang,

Anyi Rao,

Jingbo Wang,

Dahua Lin,

Bo Dai; [pdf] [arXiv]
[bibtex]
@InProceedings{Jiang_2024_CVPR, author = {Jiang, Xuekun and Rao, Anyi and Wang, Jingbo and Lin, Dahua and Dai, Bo}, title = {Cinematic Behavior Transfer via NeRF-based Differentiable Filming}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6723-6732} }
Text-Driven Image Editing via Learnable Regions: Yuanze Lin,

Yi-Wen Chen,

Yi-Hsuan Tsai,

Lu Jiang,

Ming-Hsuan Yang; [pdf] [arXiv]
[bibtex]
@InProceedings{Lin_2024_CVPR, author = {Lin, Yuanze and Chen, Yi-Wen and Tsai, Yi-Hsuan and Jiang, Lu and Yang, Ming-Hsuan}, title = {Text-Driven Image Editing via Learnable Regions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7059-7068} }
Relation Rectification in Diffusion Model: Yinwei Wu,

Xingyi Yang,

Xinchao Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2024_CVPR, author = {Wu, Yinwei and Yang, Xingyi and Wang, Xinchao}, title = {Relation Rectification in Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7685-7694} }
Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera: Jiye Lee,

Hanbyul Joo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lee_2024_CVPR, author = {Lee, Jiye and Joo, Hanbyul}, title = {Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1091-1100} }
Fast ODE-based Sampling for Diffusion Models in Around 5 Steps: Zhenyu Zhou,

Defang Chen,

Can Wang,

Chun Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2024_CVPR, author = {Zhou, Zhenyu and Chen, Defang and Wang, Can and Chen, Chun}, title = {Fast ODE-based Sampling for Diffusion Models in Around 5 Steps}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7777-7786} }
CLiC: Concept Learning in Context: Mehdi Safaee,

Aryan Mikaeili,

Or Patashnik,

Daniel Cohen-Or,

Ali Mahdavi-Amiri; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Safaee_2024_CVPR, author = {Safaee, Mehdi and Mikaeili, Aryan and Patashnik, Or and Cohen-Or, Daniel and Mahdavi-Amiri, Ali}, title = {CLiC: Concept Learning in Context}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6924-6933} }
CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention: Mohammad Sadil Khan,

Elona Dupont,

Sk Aziz Ali,

Kseniya Cherenkova,

Anis Kacem,

Djamila Aouada; [pdf] [supp]
[bibtex]
@InProceedings{Khan_2024_CVPR, author = {Khan, Mohammad Sadil and Dupont, Elona and Ali, Sk Aziz and Cherenkova, Kseniya and Kacem, Anis and Aouada, Djamila}, title = {CAD-SIGNet: CAD Language Inference from Point Clouds using Layer-wise Sketch Instance Guided Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4713-4722} }
CLIB-FIQA: Face Image Quality Assessment with Confidence Calibration: Fu-Zhao Ou,

Chongyi Li,

Shiqi Wang,

Sam Kwong; [pdf]
[bibtex]
@InProceedings{Ou_2024_CVPR, author = {Ou, Fu-Zhao and Li, Chongyi and Wang, Shiqi and Kwong, Sam}, title = {CLIB-FIQA: Face Image Quality Assessment with Confidence Calibration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1694-1704} }
Predicated Diffusion: Predicate Logic-Based Attention Guidance for Text-to-Image Diffusion Models: Kota Sueyoshi,

Takashi Matsubara; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sueyoshi_2024_CVPR, author = {Sueyoshi, Kota and Matsubara, Takashi}, title = {Predicated Diffusion: Predicate Logic-Based Attention Guidance for Text-to-Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8651-8660} }
MoML: Online Meta Adaptation for 3D Human Motion Prediction: Xiaoning Sun,

Huaijiang Sun,

Bin Li,

Dong Wei,

Weiqing Li,

Jianfeng Lu; [pdf] [supp]
[bibtex]
@InProceedings{Sun_2024_CVPR, author = {Sun, Xiaoning and Sun, Huaijiang and Li, Bin and Wei, Dong and Li, Weiqing and Lu, Jianfeng}, title = {MoML: Online Meta Adaptation for 3D Human Motion Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1042-1051} }
CAT-DM: Controllable Accelerated Virtual Try-on with Diffusion Model: Jianhao Zeng,

Dan Song,

Weizhi Nie,

Hongshuo Tian,

Tongtong Wang,

An-An Liu; [pdf] [supp]
[bibtex]
@InProceedings{Zeng_2024_CVPR, author = {Zeng, Jianhao and Song, Dan and Nie, Weizhi and Tian, Hongshuo and Wang, Tongtong and Liu, An-An}, title = {CAT-DM: Controllable Accelerated Virtual Try-on with Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8372-8382} }
Synergistic Global-space Camera and Human Reconstruction from Videos: Yizhou Zhao,

Tuanfeng Yang Wang,

Bhiksha Raj,

Min Xu,

Jimei Yang,

Chun-Hao Paul Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhao_2024_CVPR, author = {Zhao, Yizhou and Wang, Tuanfeng Yang and Raj, Bhiksha and Xu, Min and Yang, Jimei and Huang, Chun-Hao Paul}, title = {Synergistic Global-space Camera and Human Reconstruction from Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1216-1226} }
3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation: Zidu Wang,

Xiangyu Zhu,

Tianshuo Zhang,

Baiqin Wang,

Zhen Lei; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Zidu and Zhu, Xiangyu and Zhang, Tianshuo and Wang, Baiqin and Lei, Zhen}, title = {3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1672-1682} }
FreeU: Free Lunch in Diffusion U-Net: Chenyang Si,

Ziqi Huang,

Yuming Jiang,

Ziwei Liu; [pdf] [supp]
[bibtex]
@InProceedings{Si_2024_CVPR, author = {Si, Chenyang and Huang, Ziqi and Jiang, Yuming and Liu, Ziwei}, title = {FreeU: Free Lunch in Diffusion U-Net}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4733-4743} }
ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models: Lukas Höllein,

Aljaž Boži?,

Norman Müller,

David Novotny,

Hung-Yu Tseng,

Christian Richardt,

Michael Zollhöfer,

Matthias Nießner; [pdf] [supp]
[bibtex]
@InProceedings{Hollein_2024_CVPR, author = {H\"ollein, Lukas and Bo\v{z}i?, Alja\v{z} and M\"uller, Norman and Novotny, David and Tseng, Hung-Yu and Richardt, Christian and Zollh\"ofer, Michael and Nie{\ss}ner, Matthias}, title = {ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5043-5052} }
Diffusion Models Without Attention: Jing Nathan Yan,

Jiatao Gu,

Alexander M. Rush; [pdf] [arXiv]
[bibtex]
@InProceedings{Yan_2024_CVPR, author = {Yan, Jing Nathan and Gu, Jiatao and Rush, Alexander M.}, title = {Diffusion Models Without Attention}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8239-8249} }
Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion: Kiran Chhatre,

Radek Dan??ek,

Nikos Athanasiou,

Giorgio Becherini,

Christopher Peters,

Michael J. Black,

Timo Bolkart; [pdf] [supp]
[bibtex]
@InProceedings{Chhatre_2024_CVPR, author = {Chhatre, Kiran and Dan??ek, Radek and Athanasiou, Nikos and Becherini, Giorgio and Peters, Christopher and Black, Michael J. and Bolkart, Timo}, title = {Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1942-1953} }
Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation: Daichi Horita,

Naoto Inoue,

Kotaro Kikuchi,

Kota Yamaguchi,

Kiyoharu Aizawa; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Horita_2024_CVPR, author = {Horita, Daichi and Inoue, Naoto and Kikuchi, Kotaro and Yamaguchi, Kota and Aizawa, Kiyoharu}, title = {Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {67-76} }
InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning: Jing Shi,

Wei Xiong,

Zhe Lin,

Hyun Joon Jung; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shi_2024_CVPR, author = {Shi, Jing and Xiong, Wei and Lin, Zhe and Jung, Hyun Joon}, title = {InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8543-8552} }
SD2Event:Self-supervised Learning of Dynamic Detectors and Contextual Descriptors for Event Cameras: Yuan Gao,

Yuqing Zhu,

Xinjun Li,

Yimin Du,

Tianzhu Zhang; [pdf]
[bibtex]
@InProceedings{Gao_2024_CVPR, author = {Gao, Yuan and Zhu, Yuqing and Li, Xinjun and Du, Yimin and Zhang, Tianzhu}, title = {SD2Event:Self-supervised Learning of Dynamic Detectors and Contextual Descriptors for Event Cameras}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3055-3064} }
PaReNeRF: Toward Fast Large-scale Dynamic NeRF with Patch-based Reference: Xiao Tang,

Min Yang,

Penghui Sun,

Hui Li,

Yuchao Dai,

Feng Zhu,

Hojae Lee; [pdf] [supp]
[bibtex]
@InProceedings{Tang_2024_CVPR, author = {Tang, Xiao and Yang, Min and Sun, Penghui and Li, Hui and Dai, Yuchao and Zhu, Feng and Lee, Hojae}, title = {PaReNeRF: Toward Fast Large-scale Dynamic NeRF with Patch-based Reference}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5428-5438} }
Affine Equivariant Networks Based on Differential Invariants: Yikang Li,

Yeqing Qiu,

Yuxuan Chen,

Lingshen He,

Zhouchen Lin; [pdf] [supp]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Yikang and Qiu, Yeqing and Chen, Yuxuan and He, Lingshen and Lin, Zhouchen}, title = {Affine Equivariant Networks Based on Differential Invariants}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5546-5556} }
Selectively Informative Description can Reduce Undesired Embedding Entanglements in Text-to-Image Personalization: Jimyeong Kim,

Jungwon Park,

Wonjong Rhee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_CVPR, author = {Kim, Jimyeong and Park, Jungwon and Rhee, Wonjong}, title = {Selectively Informative Description can Reduce Undesired Embedding Entanglements in Text-to-Image Personalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8312-8322} }
Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models: Jiayi Guo,

Xingqian Xu,

Yifan Pu,

Zanlin Ni,

Chaofei Wang,

Manushree Vasu,

Shiji Song,

Gao Huang,

Humphrey Shi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2024_CVPR, author = {Guo, Jiayi and Xu, Xingqian and Pu, Yifan and Ni, Zanlin and Wang, Chaofei and Vasu, Manushree and Song, Shiji and Huang, Gao and Shi, Humphrey}, title = {Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7548-7558} }
FlowIE: Efficient Image Enhancement via Rectified Flow: Yixuan Zhu,

Wenliang Zhao,

Ao Li,

Yansong Tang,

Jie Zhou,

Jiwen Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhu_2024_CVPR, author = {Zhu, Yixuan and Zhao, Wenliang and Li, Ao and Tang, Yansong and Zhou, Jie and Lu, Jiwen}, title = {FlowIE: Efficient Image Enhancement via Rectified Flow}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {13-22} }
Improving Training Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architecture: Huijie Zhang,

Yifu Lu,

Ismail Alkhouri,

Saiprasad Ravishankar,

Dogyoon Song,

Qing Qu; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Huijie and Lu, Yifu and Alkhouri, Ismail and Ravishankar, Saiprasad and Song, Dogyoon and Qu, Qing}, title = {Improving Training Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architecture}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7372-7381} }
In-Context Matting: He Guo,

Zixuan Ye,

Zhiguo Cao,

Hao Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Guo_2024_CVPR, author = {Guo, He and Ye, Zixuan and Cao, Zhiguo and Lu, Hao}, title = {In-Context Matting}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3711-3720} }
DemoCaricature: Democratising Caricature Generation with a Rough Sketch: Dar-Yen Chen,

Ayan Kumar Bhunia,

Subhadeep Koley,

Aneeshan Sain,

Pinaki Nath Chowdhury,

Yi-Zhe Song; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Dar-Yen and Bhunia, Ayan Kumar and Koley, Subhadeep and Sain, Aneeshan and Chowdhury, Pinaki Nath and Song, Yi-Zhe}, title = {DemoCaricature: Democratising Caricature Generation with a Rough Sketch}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8629-8639} }
CapHuman: Capture Your Moments in Parallel Universes: Chao Liang,

Fan Ma,

Linchao Zhu,

Yingying Deng,

Yi Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liang_2024_CVPR, author = {Liang, Chao and Ma, Fan and Zhu, Linchao and Deng, Yingying and Yang, Yi}, title = {CapHuman: Capture Your Moments in Parallel Universes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6400-6409} }
SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation: Sichen Chen,

Yingyi Zhang,

Siming Huang,

Ran Yi,

Ke Fan,

Ruixin Zhang,

Peixian Chen,

Jun Wang,

Shouhong Ding,

Lizhuang Ma; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Sichen and Zhang, Yingyi and Huang, Siming and Yi, Ran and Fan, Ke and Zhang, Ruixin and Chen, Peixian and Wang, Jun and Ding, Shouhong and Ma, Lizhuang}, title = {SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1082-1090} }
Authentic Hand Avatar from a Phone Scan via Universal Hand Model: Gyeongsik Moon,

Weipeng Xu,

Rohan Joshi,

Chenglei Wu,

Takaaki Shiratori; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Moon_2024_CVPR, author = {Moon, Gyeongsik and Xu, Weipeng and Joshi, Rohan and Wu, Chenglei and Shiratori, Takaaki}, title = {Authentic Hand Avatar from a Phone Scan via Universal Hand Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2029-2038} }
Open-World Semantic Segmentation Including Class Similarity: Matteo Sodano,

Federico Magistri,

Lucas Nunes,

Jens Behley,

Cyrill Stachniss; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sodano_2024_CVPR, author = {Sodano, Matteo and Magistri, Federico and Nunes, Lucas and Behley, Jens and Stachniss, Cyrill}, title = {Open-World Semantic Segmentation Including Class Similarity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3184-3194} }
Towards Memorization-Free Diffusion Models: Chen Chen,

Daochang Liu,

Chang Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Chen and Liu, Daochang and Xu, Chang}, title = {Towards Memorization-Free Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8425-8434} }
IQ-VFI: Implicit Quadratic Motion Estimation for Video Frame Interpolation: Mengshun Hu,

Kui Jiang,

Zhihang Zhong,

Zheng Wang,

Yinqiang Zheng; [pdf]
[bibtex]
@InProceedings{Hu_2024_CVPR, author = {Hu, Mengshun and Jiang, Kui and Zhong, Zhihang and Wang, Zheng and Zheng, Yinqiang}, title = {IQ-VFI: Implicit Quadratic Motion Estimation for Video Frame Interpolation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6410-6419} }
KeyPoint Relative Position Encoding for Face Recognition: Minchul Kim,

Yiyang Su,

Feng Liu,

Anil Jain,

Xiaoming Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_CVPR, author = {Kim, Minchul and Su, Yiyang and Liu, Feng and Jain, Anil and Liu, Xiaoming}, title = {KeyPoint Relative Position Encoding for Face Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {244-255} }
Hyper-MD: Mesh Denoising with Customized Parameters Aware of Noise Intensity and Geometric Characteristics: Xingtao Wang,

Hongliang Wei,

Xiaopeng Fan,

Debin Zhao; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Xingtao and Wei, Hongliang and Fan, Xiaopeng and Zhao, Debin}, title = {Hyper-MD: Mesh Denoising with Customized Parameters Aware of Noise Intensity and Geometric Characteristics}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4651-4660} }
Beyond First-Order Tweedie: Solving Inverse Problems using Latent Diffusion: Litu Rout,

Yujia Chen,

Abhishek Kumar,

Constantine Caramanis,

Sanjay Shakkottai,

Wen-Sheng Chu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rout_2024_CVPR, author = {Rout, Litu and Chen, Yujia and Kumar, Abhishek and Caramanis, Constantine and Shakkottai, Sanjay and Chu, Wen-Sheng}, title = {Beyond First-Order Tweedie: Solving Inverse Problems using Latent Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9472-9481} }
Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis: Yuchao Gu,

Xintao Wang,

Yixiao Ge,

Ying Shan,

Mike Zheng Shou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gu_2024_CVPR, author = {Gu, Yuchao and Wang, Xintao and Ge, Yixiao and Shan, Ying and Shou, Mike Zheng}, title = {Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7631-7640} }
Continuous Pose for Monocular Cameras in Neural Implicit Representation: Qi Ma,

Danda Pani Paudel,

Ajad Chhatkuli,

Luc Van Gool; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ma_2024_CVPR, author = {Ma, Qi and Paudel, Danda Pani and Chhatkuli, Ajad and Van Gool, Luc}, title = {Continuous Pose for Monocular Cameras in Neural Implicit Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5291-5301} }
D^4: Dataset Distillation via Disentangled Diffusion Model: Duo Su,

Junjie Hou,

Weizhi Gao,

Yingjie Tian,

Bowen Tang; [pdf] [supp]
[bibtex]
@InProceedings{Su_2024_CVPR, author = {Su, Duo and Hou, Junjie and Gao, Weizhi and Tian, Yingjie and Tang, Bowen}, title = {D{\textasciicircum}4: Dataset Distillation via Disentangled Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5809-5818} }
360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model: Qian Wang,

Weiqi Li,

Chong Mou,

Xinhua Cheng,

Jian Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Qian and Li, Weiqi and Mou, Chong and Cheng, Xinhua and Zhang, Jian}, title = {360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6913-6923} }
RankMatch: Exploring the Better Consistency Regularization for Semi-supervised Semantic Segmentation: Huayu Mai,

Rui Sun,

Tianzhu Zhang,

Feng Wu; [pdf]
[bibtex]
@InProceedings{Mai_2024_CVPR, author = {Mai, Huayu and Sun, Rui and Zhang, Tianzhu and Wu, Feng}, title = {RankMatch: Exploring the Better Consistency Regularization for Semi-supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3391-3401} }
DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation: Yuanchen Wu,

Xichen Ye,

Kequan Yang,

Jide Li,

Xiaoqiang Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2024_CVPR, author = {Wu, Yuanchen and Ye, Xichen and Yang, Kequan and Li, Jide and Li, Xiaoqiang}, title = {DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3534-3543} }
SurMo: Surface-based 4D Motion Modeling for Dynamic Human Rendering: Tao Hu,

Fangzhou Hong,

Ziwei Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hu_2024_CVPR, author = {Hu, Tao and Hong, Fangzhou and Liu, Ziwei}, title = {SurMo: Surface-based 4D Motion Modeling for Dynamic Human Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6550-6560} }
Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation: Zhiwu Qing,

Shiwei Zhang,

Jiayu Wang,

Xiang Wang,

Yujie Wei,

Yingya Zhang,

Changxin Gao,

Nong Sang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qing_2024_CVPR, author = {Qing, Zhiwu and Zhang, Shiwei and Wang, Jiayu and Wang, Xiang and Wei, Yujie and Zhang, Yingya and Gao, Changxin and Sang, Nong}, title = {Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6635-6645} }
PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis: Zhengyao Lv,

Yuxiang Wei,

Wangmeng Zuo,

Kwan-Yee K. Wong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lv_2024_CVPR, author = {Lv, Zhengyao and Wei, Yuxiang and Zuo, Wangmeng and Wong, Kwan-Yee K.}, title = {PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9264-9274} }
Exploring Efficient Asymmetric Blind-Spots for Self-Supervised Denoising in Real-World Scenarios: Shiyan Chen,

Jiyuan Zhang,

Zhaofei Yu,

Tiejun Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Shiyan and Zhang, Jiyuan and Yu, Zhaofei and Huang, Tiejun}, title = {Exploring Efficient Asymmetric Blind-Spots for Self-Supervised Denoising in Real-World Scenarios}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2814-2823} }
Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring: Xin Gao,

Tianheng Qiu,

Xinyu Zhang,

Hanlin Bai,

Kang Liu,

Xuan Huang,

Hu Wei,

Guoying Zhang,

Huaping Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gao_2024_CVPR, author = {Gao, Xin and Qiu, Tianheng and Zhang, Xinyu and Bai, Hanlin and Liu, Kang and Huang, Xuan and Wei, Hu and Zhang, Guoying and Liu, Huaping}, title = {Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2733-2742} }
MaskPLAN: Masked Generative Layout Planning from Partial Input: Hang Zhang,

Anton Savov,

Benjamin Dillenburger; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Hang and Savov, Anton and Dillenburger, Benjamin}, title = {MaskPLAN: Masked Generative Layout Planning from Partial Input}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8964-8973} }
HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observations: Peng Dai,

Yang Zhang,

Tao Liu,

Zhen Fan,

Tianyuan Du,

Zhuo Su,

Xiaozheng Zheng,

Zeming Li; [pdf] [supp]
[bibtex]
@InProceedings{Dai_2024_CVPR, author = {Dai, Peng and Zhang, Yang and Liu, Tao and Fan, Zhen and Du, Tianyuan and Su, Zhuo and Zheng, Xiaozheng and Li, Zeming}, title = {HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {874-884} }
Flexible Biometrics Recognition: Bridging the Multimodality Gap through Attention Alignment and Prompt Tuning: Leslie Ching Ow Tiong,

Dick Sigmund,

Chen-Hui Chan,

Andrew Beng Jin Teoh; [pdf] [supp]
[bibtex]
@InProceedings{Tiong_2024_CVPR, author = {Tiong, Leslie Ching Ow and Sigmund, Dick and Chan, Chen-Hui and Teoh, Andrew Beng Jin}, title = {Flexible Biometrics Recognition: Bridging the Multimodality Gap through Attention Alignment and Prompt Tuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {267-276} }
Multi-scale Dynamic and Hierarchical Relationship Modeling for Facial Action Units Recognition: Zihan Wang,

Siyang Song,

Cheng Luo,

Songhe Deng,

Weicheng Xie,

Linlin Shen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Zihan and Song, Siyang and Luo, Cheng and Deng, Songhe and Xie, Weicheng and Shen, Linlin}, title = {Multi-scale Dynamic and Hierarchical Relationship Modeling for Facial Action Units Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1270-1280} }
EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams: Christen Millerdurai,

Hiroyasu Akada,

Jian Wang,

Diogo Luvizon,

Christian Theobalt,

Vladislav Golyanik; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Millerdurai_2024_CVPR, author = {Millerdurai, Christen and Akada, Hiroyasu and Wang, Jian and Luvizon, Diogo and Theobalt, Christian and Golyanik, Vladislav}, title = {EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1186-1195} }
A Call to Reflect on Evaluation Practices for Age Estimation: Comparative Analysis of the State-of-the-Art and a Unified Benchmark: Jakub Paplhám,

Vojt?ch Franc; [pdf] [supp]
[bibtex]
@InProceedings{Paplham_2024_CVPR, author = {Paplh\'am, Jakub and Franc, Vojt?ch}, title = {A Call to Reflect on Evaluation Practices for Age Estimation: Comparative Analysis of the State-of-the-Art and a Unified Benchmark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1196-1205} }
CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detection: Jiayi Zhu,

Qing Guo,

Felix Juefei-Xu,

Yihao Huang,

Yang Liu,

Geguang Pu; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhu_2024_CVPR, author = {Zhu, Jiayi and Guo, Qing and Juefei-Xu, Felix and Huang, Yihao and Liu, Yang and Pu, Geguang}, title = {CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3669-3678} }
MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation: Sumanth Udupa,

Prajwal Gurunath,

Aniruddh Sikdar,

Suresh Sundaram; [pdf] [supp]
[bibtex]
@InProceedings{Udupa_2024_CVPR, author = {Udupa, Sumanth and Gurunath, Prajwal and Sikdar, Aniruddh and Sundaram, Suresh}, title = {MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5904-5914} }
MotionEditor: Editing Video Motion via Content-Aware Diffusion: Shuyuan Tu,

Qi Dai,

Zhi-Qi Cheng,

Han Hu,

Xintong Han,

Zuxuan Wu,

Yu-Gang Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tu_2024_CVPR, author = {Tu, Shuyuan and Dai, Qi and Cheng, Zhi-Qi and Hu, Han and Han, Xintong and Wu, Zuxuan and Jiang, Yu-Gang}, title = {MotionEditor: Editing Video Motion via Content-Aware Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7882-7891} }
Doubly Abductive Counterfactual Inference for Text-based Image Editing: Xue Song,

Jiequan Cui,

Hanwang Zhang,

Jingjing Chen,

Richang Hong,

Yu-Gang Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Song_2024_CVPR, author = {Song, Xue and Cui, Jiequan and Zhang, Hanwang and Chen, Jingjing and Hong, Richang and Jiang, Yu-Gang}, title = {Doubly Abductive Counterfactual Inference for Text-based Image Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9162-9171} }
Normalizing Flows on the Product Space of SO(3) Manifolds for Probabilistic Human Pose Modeling: Olaf Dünkel,

Tim Salzmann,

Florian Pfaff; [pdf] [supp]
[bibtex]
@InProceedings{Dunkel_2024_CVPR, author = {D\"unkel, Olaf and Salzmann, Tim and Pfaff, Florian}, title = {Normalizing Flows on the Product Space of SO(3) Manifolds for Probabilistic Human Pose Modeling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2285-2294} }
ReGenNet: Towards Human Action-Reaction Synthesis: Liang Xu,

Yizhou Zhou,

Yichao Yan,

Xin Jin,

Wenhan Zhu,

Fengyun Rao,

Xiaokang Yang,

Wenjun Zeng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2024_CVPR, author = {Xu, Liang and Zhou, Yizhou and Yan, Yichao and Jin, Xin and Zhu, Wenhan and Rao, Fengyun and Yang, Xiaokang and Zeng, Wenjun}, title = {ReGenNet: Towards Human Action-Reaction Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1759-1769} }
A Simple Baseline for Efficient Hand Mesh Reconstruction: Zhishan Zhou,

Shihao Zhou,

Zhi Lv,

Minqiang Zou,

Yao Tang,

Jiajun Liang; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhou_2024_CVPR, author = {Zhou, Zhishan and Zhou, Shihao and Lv, Zhi and Zou, Minqiang and Tang, Yao and Liang, Jiajun}, title = {A Simple Baseline for Efficient Hand Mesh Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1367-1376} }
PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding: Zhen Li,

Mingdeng Cao,

Xintao Wang,

Zhongang Qi,

Ming-Ming Cheng,

Ying Shan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Zhen and Cao, Mingdeng and Wang, Xintao and Qi, Zhongang and Cheng, Ming-Ming and Shan, Ying}, title = {PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8640-8650} }
Score-Guided Diffusion for 3D Human Recovery: Anastasis Stathopoulos,

Ligong Han,

Dimitris Metaxas; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Stathopoulos_2024_CVPR, author = {Stathopoulos, Anastasis and Han, Ligong and Metaxas, Dimitris}, title = {Score-Guided Diffusion for 3D Human Recovery}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {906-915} }
Check Locate Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation: Biao Gong,

Siteng Huang,

Yutong Feng,

Shiwei Zhang,

Yuyuan Li,

Yu Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gong_2024_CVPR, author = {Gong, Biao and Huang, Siteng and Feng, Yutong and Zhang, Shiwei and Li, Yuyuan and Liu, Yu}, title = {Check Locate Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6624-6634} }
Pose-Transformed Equivariant Network for 3D Point Trajectory Prediction: Ruixuan Yu,

Jian Sun; [pdf] [supp]
[bibtex]
@InProceedings{Yu_2024_CVPR, author = {Yu, Ruixuan and Sun, Jian}, title = {Pose-Transformed Equivariant Network for 3D Point Trajectory Prediction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5503-5512} }
Revisiting Sampson Approximations for Geometric Estimation Problems: Felix Rydell,

Angélica Torres,

Viktor Larsson; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rydell_2024_CVPR, author = {Rydell, Felix and Torres, Ang\'elica and Larsson, Viktor}, title = {Revisiting Sampson Approximations for Geometric Estimation Problems}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4990-4998} }
Fixed Point Diffusion Models: Xingjian Bai,

Luke Melas-Kyriazi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bai_2024_CVPR, author = {Bai, Xingjian and Melas-Kyriazi, Luke}, title = {Fixed Point Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9430-9440} }
Residual Learning in Diffusion Models: Junyu Zhang,

Daochang Liu,

Eunbyung Park,

Shichao Zhang,

Chang Xu; [pdf]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Junyu and Liu, Daochang and Park, Eunbyung and Zhang, Shichao and Xu, Chang}, title = {Residual Learning in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7289-7299} }
Beyond Textual Constraints: Learning Novel Diffusion Conditions with Fewer Examples: Yuyang Yu,

Bangzhen Liu,

Chenxi Zheng,

Xuemiao Xu,

Huaidong Zhang,

Shengfeng He; [pdf] [supp]
[bibtex]
@InProceedings{Yu_2024_CVPR, author = {Yu, Yuyang and Liu, Bangzhen and Zheng, Chenxi and Xu, Xuemiao and Zhang, Huaidong and He, Shengfeng}, title = {Beyond Textual Constraints: Learning Novel Diffusion Conditions with Fewer Examples}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7109-7118} }
Exploiting Style Latent Flows for Generalizing Deepfake Video Detection: Jongwook Choi,

Taehoon Kim,

Yonghyun Jeong,

Seungryul Baek,

Jongwon Choi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Choi_2024_CVPR, author = {Choi, Jongwook and Kim, Taehoon and Jeong, Yonghyun and Baek, Seungryul and Choi, Jongwon}, title = {Exploiting Style Latent Flows for Generalizing Deepfake Video Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1133-1143} }
Video-P2P: Video Editing with Cross-attention Control: Shaoteng Liu,

Yuechen Zhang,

Wenbo Li,

Zhe Lin,

Jiaya Jia; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Shaoteng and Zhang, Yuechen and Li, Wenbo and Lin, Zhe and Jia, Jiaya}, title = {Video-P2P: Video Editing with Cross-attention Control}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8599-8608} }
Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentation: Feilong Tang,

Zhongxing Xu,

Zhaojun Qu,

Wei Feng,

Xingjian Jiang,

Zongyuan Ge; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tang_2024_CVPR, author = {Tang, Feilong and Xu, Zhongxing and Qu, Zhaojun and Feng, Wei and Jiang, Xingjian and Ge, Zongyuan}, title = {Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3324-3334} }
PIE-NeRF: Physics-based Interactive Elastodynamics with NeRF: Yutao Feng,

Yintong Shang,

Xuan Li,

Tianjia Shao,

Chenfanfu Jiang,

Yin Yang; [pdf] [supp]
[bibtex]
@InProceedings{Feng_2024_CVPR, author = {Feng, Yutao and Shang, Yintong and Li, Xuan and Shao, Tianjia and Jiang, Chenfanfu and Yang, Yin}, title = {PIE-NeRF: Physics-based Interactive Elastodynamics with NeRF}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4450-4461} }
FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding: Jun Xiang,

Xuan Gao,

Yudong Guo,

Juyong Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xiang_2024_CVPR, author = {Xiang, Jun and Gao, Xuan and Guo, Yudong and Zhang, Juyong}, title = {FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1802-1812} }
ZERO-IG: Zero-Shot Illumination-Guided Joint Denoising and Adaptive Enhancement for Low-Light Images: Yiqi Shi,

Duo Liu,

Liguo Zhang,

Ye Tian,

Xuezhi Xia,

Xiaojing Fu; [pdf] [supp]
[bibtex]
@InProceedings{Shi_2024_CVPR, author = {Shi, Yiqi and Liu, Duo and Zhang, Liguo and Tian, Ye and Xia, Xuezhi and Fu, Xiaojing}, title = {ZERO-IG: Zero-Shot Illumination-Guided Joint Denoising and Adaptive Enhancement for Low-Light Images}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3015-3024} }
FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models: Jinglin Xu,

Yijie Guo,

Yuxin Peng; [pdf] [arXiv]
[bibtex]
@InProceedings{Xu_2024_CVPR, author = {Xu, Jinglin and Guo, Yijie and Peng, Yuxin}, title = {FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {561-570} }
DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling: Linqi Zhou,

Andy Shih,

Chenlin Meng,

Stefano Ermon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhou_2024_CVPR, author = {Zhou, Linqi and Shih, Andy and Meng, Chenlin and Ermon, Stefano}, title = {DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4610-4619} }
Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs: Hao Fei,

Shengqiong Wu,

Wei Ji,

Hanwang Zhang,

Tat-Seng Chua; [pdf] [supp]
[bibtex]
@InProceedings{Fei_2024_CVPR, author = {Fei, Hao and Wu, Shengqiong and Ji, Wei and Zhang, Hanwang and Chua, Tat-Seng}, title = {Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7641-7653} }
General Object Foundation Model for Images and Videos at Scale: Junfeng Wu,

Yi Jiang,

Qihao Liu,

Zehuan Yuan,

Xiang Bai,

Song Bai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2024_CVPR, author = {Wu, Junfeng and Jiang, Yi and Liu, Qihao and Yuan, Zehuan and Bai, Xiang and Bai, Song}, title = {General Object Foundation Model for Images and Videos at Scale}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3783-3795} }
Inlier Confidence Calibration for Point Cloud Registration: Yongzhe Yuan,

Yue Wu,

Xiaolong Fan,

Maoguo Gong,

Qiguang Miao,

Wenping Ma; [pdf] [supp]
[bibtex]
@InProceedings{Yuan_2024_CVPR, author = {Yuan, Yongzhe and Wu, Yue and Fan, Xiaolong and Gong, Maoguo and Miao, Qiguang and Ma, Wenping}, title = {Inlier Confidence Calibration for Point Cloud Registration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5312-5321} }
Readout Guidance: Learning Control from Diffusion Features: Grace Luo,

Trevor Darrell,

Oliver Wang,

Dan B Goldman,

Aleksander Holynski; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Luo_2024_CVPR, author = {Luo, Grace and Darrell, Trevor and Wang, Oliver and Goldman, Dan B and Holynski, Aleksander}, title = {Readout Guidance: Learning Control from Diffusion Features}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8217-8227} }
A Unified Approach for Text- and Image-guided 4D Scene Generation: Yufeng Zheng,

Xueting Li,

Koki Nagano,

Sifei Liu,

Otmar Hilliges,

Shalini De Mello; [pdf] [supp]
[bibtex]
@InProceedings{Zheng_2024_CVPR, author = {Zheng, Yufeng and Li, Xueting and Nagano, Koki and Liu, Sifei and Hilliges, Otmar and De Mello, Shalini}, title = {A Unified Approach for Text- and Image-guided 4D Scene Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7300-7309} }
GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians: Liangxiao Hu,

Hongwen Zhang,

Yuxiang Zhang,

Boyao Zhou,

Boning Liu,

Shengping Zhang,

Liqiang Nie; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hu_2024_CVPR, author = {Hu, Liangxiao and Zhang, Hongwen and Zhang, Yuxiang and Zhou, Boyao and Liu, Boning and Zhang, Shengping and Nie, Liqiang}, title = {GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {634-644} }
Mosaic-SDF for 3D Generative Models: Lior Yariv,

Omri Puny,

Oran Gafni,

Yaron Lipman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yariv_2024_CVPR, author = {Yariv, Lior and Puny, Omri and Gafni, Oran and Lipman, Yaron}, title = {Mosaic-SDF for 3D Generative Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4630-4639} }
Diffusion Handles Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D: Karran Pandey,

Paul Guerrero,

Matheus Gadelha,

Yannick Hold-Geoffroy,

Karan Singh,

Niloy J. Mitra; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Pandey_2024_CVPR, author = {Pandey, Karran and Guerrero, Paul and Gadelha, Matheus and Hold-Geoffroy, Yannick and Singh, Karan and Mitra, Niloy J.}, title = {Diffusion Handles Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7695-7704} }
Friendly Sharpness-Aware Minimization: Tao Li,

Pan Zhou,

Zhengbao He,

Xinwen Cheng,

Xiaolin Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Tao and Zhou, Pan and He, Zhengbao and Cheng, Xinwen and Huang, Xiaolin}, title = {Friendly Sharpness-Aware Minimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5631-5640} }
BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models: Fengyuan Shi,

Jiaxi Gu,

Hang Xu,

Songcen Xu,

Wei Zhang,

Limin Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shi_2024_CVPR, author = {Shi, Fengyuan and Gu, Jiaxi and Xu, Hang and Xu, Songcen and Zhang, Wei and Wang, Limin}, title = {BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7393-7402} }
NC-TTT: A Noise Constrastive Approach for Test-Time Training: David Osowiechi,

Gustavo A. Vargas Hakim,

Mehrdad Noori,

Milad Cheraghalikhani,

Ali Bahri,

Moslem Yazdanpanah,

Ismail Ben Ayed,

Christian Desrosiers; [pdf] [supp]
[bibtex]
@InProceedings{Osowiechi_2024_CVPR, author = {Osowiechi, David and Hakim, Gustavo A. Vargas and Noori, Mehrdad and Cheraghalikhani, Milad and Bahri, Ali and Yazdanpanah, Moslem and Ben Ayed, Ismail and Desrosiers, Christian}, title = {NC-TTT: A Noise Constrastive Approach for Test-Time Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6078-6086} }
Small Scale Data-Free Knowledge Distillation: He Liu,

Yikai Wang,

Huaping Liu,

Fuchun Sun,

Anbang Yao; [pdf] [arXiv]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, He and Wang, Yikai and Liu, Huaping and Sun, Fuchun and Yao, Anbang}, title = {Small Scale Data-Free Knowledge Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6008-6016} }
CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing: Ajian Liu,

Shuai Xue,

Jianwen Gan,

Jun Wan,

Yanyan Liang,

Jiankang Deng,

Sergio Escalera,

Zhen Lei; [pdf]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Ajian and Xue, Shuai and Gan, Jianwen and Wan, Jun and Liang, Yanyan and Deng, Jiankang and Escalera, Sergio and Lei, Zhen}, title = {CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {222-232} }
Open Vocabulary Semantic Scene Sketch Understanding: Ahmed Bourouis,

Judith E. Fan,

Yulia Gryaditskaya; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bourouis_2024_CVPR, author = {Bourouis, Ahmed and Fan, Judith E. and Gryaditskaya, Yulia}, title = {Open Vocabulary Semantic Scene Sketch Understanding}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4176-4186} }
IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing: Shaofei Wang,

Bozidar Antic,

Andreas Geiger,

Siyu Tang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Shaofei and Antic, Bozidar and Geiger, Andreas and Tang, Siyu}, title = {IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1877-1888} }
Efficient Detection of Long Consistent Cycles and its Application to Distributed Synchronization: Shaohan Li,

Yunpeng Shi,

Gilad Lerman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Shaohan and Shi, Yunpeng and Lerman, Gilad}, title = {Efficient Detection of Long Consistent Cycles and its Application to Distributed Synchronization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5260-5269} }
Vlogger: Make Your Dream A Vlog: Shaobin Zhuang,

Kunchang Li,

Xinyuan Chen,

Yaohui Wang,

Ziwei Liu,

Yu Qiao,

Yali Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhuang_2024_CVPR, author = {Zhuang, Shaobin and Li, Kunchang and Chen, Xinyuan and Wang, Yaohui and Liu, Ziwei and Qiao, Yu and Wang, Yali}, title = {Vlogger: Make Your Dream A Vlog}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8806-8817} }
Neural 3D Strokes: Creating Stylized 3D Scenes with Vectorized 3D Strokes: Hao-Bin Duan,

Miao Wang,

Yan-Xun Li,

Yong-Liang Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Duan_2024_CVPR, author = {Duan, Hao-Bin and Wang, Miao and Li, Yan-Xun and Yang, Yong-Liang}, title = {Neural 3D Strokes: Creating Stylized 3D Scenes with Vectorized 3D Strokes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5240-5249} }
Multi-Object Tracking in the Dark: Xinzhe Wang,

Kang Ma,

Qiankun Liu,

Yunhao Zou,

Ying Fu; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Xinzhe and Ma, Kang and Liu, Qiankun and Zou, Yunhao and Fu, Ying}, title = {Multi-Object Tracking in the Dark}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {382-392} }
UniHuman: A Unified Model For Editing Human Images in the Wild: Nannan Li,

Qing Liu,

Krishna Kumar Singh,

Yilin Wang,

Jianming Zhang,

Bryan A. Plummer,

Zhe Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Nannan and Liu, Qing and Singh, Krishna Kumar and Wang, Yilin and Zhang, Jianming and Plummer, Bryan A. and Lin, Zhe}, title = {UniHuman: A Unified Model For Editing Human Images in the Wild}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2039-2048} }
DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Model: Lirui Zhao,

Yue Yang,

Kaipeng Zhang,

Wenqi Shao,

Yuxin Zhang,

Yu Qiao,

Ping Luo,

Rongrong Ji; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhao_2024_CVPR, author = {Zhao, Lirui and Yang, Yue and Zhang, Kaipeng and Shao, Wenqi and Zhang, Yuxin and Qiao, Yu and Luo, Ping and Ji, Rongrong}, title = {DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6390-6399} }
In Search of a Data Transformation That Accelerates Neural Field Training: Junwon Seo,

Sangyoon Lee,

Kwang In Kim,

Jaeho Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Seo_2024_CVPR, author = {Seo, Junwon and Lee, Sangyoon and Kim, Kwang In and Lee, Jaeho}, title = {In Search of a Data Transformation That Accelerates Neural Field Training}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4830-4839} }
Zero-Painter: Training-Free Layout Control for Text-to-Image Synthesis: Marianna Ohanyan,

Hayk Manukyan,

Zhangyang Wang,

Shant Navasardyan,

Humphrey Shi; [pdf] [supp]
[bibtex]
@InProceedings{Ohanyan_2024_CVPR, author = {Ohanyan, Marianna and Manukyan, Hayk and Wang, Zhangyang and Navasardyan, Shant and Shi, Humphrey}, title = {Zero-Painter: Training-Free Layout Control for Text-to-Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8764-8774} }
Towards 3D Vision with Low-Cost Single-Photon Cameras: Fangzhou Mu,

Carter Sifferman,

Sacha Jungerman,

Yiquan Li,

Mark Han,

Michael Gleicher,

Mohit Gupta,

Yin Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mu_2024_CVPR, author = {Mu, Fangzhou and Sifferman, Carter and Jungerman, Sacha and Li, Yiquan and Han, Mark and Gleicher, Michael and Gupta, Mohit and Li, Yin}, title = {Towards 3D Vision with Low-Cost Single-Photon Cameras}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5302-5311} }
WonderJourney: Going from Anywhere to Everywhere: Hong-Xing Yu,

Haoyi Duan,

Junhwa Hur,

Kyle Sargent,

Michael Rubinstein,

William T. Freeman,

Forrester Cole,

Deqing Sun,

Noah Snavely,

Jiajun Wu,

Charles Herrmann; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yu_2024_CVPR, author = {Yu, Hong-Xing and Duan, Haoyi and Hur, Junhwa and Sargent, Kyle and Rubinstein, Michael and Freeman, William T. and Cole, Forrester and Sun, Deqing and Snavely, Noah and Wu, Jiajun and Herrmann, Charles}, title = {WonderJourney: Going from Anywhere to Everywhere}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6658-6667} }
4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling: Sherwin Bahmani,

Ivan Skorokhodov,

Victor Rong,

Gordon Wetzstein,

Leonidas Guibas,

Peter Wonka,

Sergey Tulyakov,

Jeong Joon Park,

Andrea Tagliasacchi,

David B. Lindell; [pdf] [supp]
[bibtex]
@InProceedings{Bahmani_2024_CVPR, author = {Bahmani, Sherwin and Skorokhodov, Ivan and Rong, Victor and Wetzstein, Gordon and Guibas, Leonidas and Wonka, Peter and Tulyakov, Sergey and Park, Jeong Joon and Tagliasacchi, Andrea and Lindell, David B.}, title = {4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7996-8006} }
FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition: Sicheng Mo,

Fangzhou Mu,

Kuan Heng Lin,

Yanli Liu,

Bochen Guan,

Yin Li,

Bolei Zhou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mo_2024_CVPR, author = {Mo, Sicheng and Mu, Fangzhou and Lin, Kuan Heng and Liu, Yanli and Guan, Bochen and Li, Yin and Zhou, Bolei}, title = {FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7465-7475} }
VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models: Hyeonho Jeong,

Geon Yeong Park,

Jong Chul Ye; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jeong_2024_CVPR, author = {Jeong, Hyeonho and Park, Geon Yeong and Ye, Jong Chul}, title = {VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9212-9221} }
DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models: Muyang Li,

Tianle Cai,

Jiaxin Cao,

Qinsheng Zhang,

Han Cai,

Junjie Bai,

Yangqing Jia,

Kai Li,

Song Han; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Muyang and Cai, Tianle and Cao, Jiaxin and Zhang, Qinsheng and Cai, Han and Bai, Junjie and Jia, Yangqing and Li, Kai and Han, Song}, title = {DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7183-7193} }
AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search: Junghyup Lee,

Bumsub Ham; [pdf] [supp]
[bibtex]
@InProceedings{Lee_2024_CVPR, author = {Lee, Junghyup and Ham, Bumsub}, title = {AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5893-5903} }
Improving Physics-Augmented Continuum Neural Radiance Field-Based Geometry-Agnostic System Identification with Lagrangian Particle Optimization: Takuhiro Kaneko; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kaneko_2024_CVPR, author = {Kaneko, Takuhiro}, title = {Improving Physics-Augmented Continuum Neural Radiance Field-Based Geometry-Agnostic System Identification with Lagrangian Particle Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5470-5480} }
Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual Loss: Jaeha Kim,

Junghun Oh,

Kyoung Mu Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_CVPR, author = {Kim, Jaeha and Oh, Junghun and Lee, Kyoung Mu}, title = {Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual Loss}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2651-2661} }
XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies: Xuanchi Ren,

Jiahui Huang,

Xiaohui Zeng,

Ken Museth,

Sanja Fidler,

Francis Williams; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ren_2024_CVPR, author = {Ren, Xuanchi and Huang, Jiahui and Zeng, Xiaohui and Museth, Ken and Fidler, Sanja and Williams, Francis}, title = {XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4209-4219} }
Reconstruction-free Cascaded Adaptive Compressive Sensing: Chenxi Qiu,

Tao Yue,

Xuemei Hu; [pdf]
[bibtex]
@InProceedings{Qiu_2024_CVPR, author = {Qiu, Chenxi and Yue, Tao and Hu, Xuemei}, title = {Reconstruction-free Cascaded Adaptive Compressive Sensing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2620-2630} }
USE: Universal Segment Embeddings for Open-Vocabulary Image Segmentation: Xiaoqi Wang,

Wenbin He,

Xiwei Xuan,

Clint Sebastian,

Jorge Piazentin Ono,

Xin Li,

Sima Behpour,

Thang Doan,

Liang Gou,

Han-Wei Shen,

Liu Ren; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Xiaoqi and He, Wenbin and Xuan, Xiwei and Sebastian, Clint and Ono, Jorge Piazentin and Li, Xin and Behpour, Sima and Doan, Thang and Gou, Liang and Shen, Han-Wei and Ren, Liu}, title = {USE: Universal Segment Embeddings for Open-Vocabulary Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4187-4196} }
Functional Diffusion: Biao Zhang,

Peter Wonka; [pdf] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Biao and Wonka, Peter}, title = {Functional Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4723-4732} }
Wired Perspectives: Multi-View Wire Art Embraces Generative AI: Zhiyu Qu,

Lan Yang,

Honggang Zhang,

Tao Xiang,

Kaiyue Pang,

Yi-Zhe Song; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Qu_2024_CVPR, author = {Qu, Zhiyu and Yang, Lan and Zhang, Honggang and Xiang, Tao and Pang, Kaiyue and Song, Yi-Zhe}, title = {Wired Perspectives: Multi-View Wire Art Embraces Generative AI}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6149-6158} }
Leveraging Camera Triplets for Efficient and Accurate Structure-from-Motion: Lalit Manam,

Venu Madhav Govindu; [pdf] [supp]
[bibtex]
@InProceedings{Manam_2024_CVPR, author = {Manam, Lalit and Govindu, Venu Madhav}, title = {Leveraging Camera Triplets for Efficient and Accurate Structure-from-Motion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4959-4968} }
SimDA: Simple Diffusion Adapter for Efficient Video Generation: Zhen Xing,

Qi Dai,

Han Hu,

Zuxuan Wu,

Yu-Gang Jiang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xing_2024_CVPR, author = {Xing, Zhen and Dai, Qi and Hu, Han and Wu, Zuxuan and Jiang, Yu-Gang}, title = {SimDA: Simple Diffusion Adapter for Efficient Video Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7827-7839} }
Multi-view Aggregation Network for Dichotomous Image Segmentation: Qian Yu,

Xiaoqi Zhao,

Youwei Pang,

Lihe Zhang,

Huchuan Lu; [pdf] [arXiv]
[bibtex]
@InProceedings{Yu_2024_CVPR, author = {Yu, Qian and Zhao, Xiaoqi and Pang, Youwei and Zhang, Lihe and Lu, Huchuan}, title = {Multi-view Aggregation Network for Dichotomous Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3921-3930} }
A Recipe for Scaling up Text-to-Video Generation with Text-free Videos: Xiang Wang,

Shiwei Zhang,

Hangjie Yuan,

Zhiwu Qing,

Biao Gong,

Yingya Zhang,

Yujun Shen,

Changxin Gao,

Nong Sang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Xiang and Zhang, Shiwei and Yuan, Hangjie and Qing, Zhiwu and Gong, Biao and Zhang, Yingya and Shen, Yujun and Gao, Changxin and Sang, Nong}, title = {A Recipe for Scaling up Text-to-Video Generation with Text-free Videos}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6572-6582} }
Molecular Data Programming: Towards Molecule Pseudo-labeling with Systematic Weak Supervision: Xin Juan,

Kaixiong Zhou,

Ninghao Liu,

Tianlong Chen,

Xin Wang; [pdf] [supp]
[bibtex]
@InProceedings{Juan_2024_CVPR, author = {Juan, Xin and Zhou, Kaixiong and Liu, Ninghao and Chen, Tianlong and Wang, Xin}, title = {Molecular Data Programming: Towards Molecule Pseudo-labeling with Systematic Weak Supervision}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {308-318} }
Residual Denoising Diffusion Models: Jiawei Liu,

Qiang Wang,

Huijie Fan,

Yinong Wang,

Yandong Tang,

Liangqiong Qu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Jiawei and Wang, Qiang and Fan, Huijie and Wang, Yinong and Tang, Yandong and Qu, Liangqiong}, title = {Residual Denoising Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2773-2783} }
Towards Accurate and Robust Architectures via Neural Architecture Search: Yuwei Ou,

Yuqi Feng,

Yanan Sun; [pdf] [arXiv]
[bibtex]
@InProceedings{Ou_2024_CVPR, author = {Ou, Yuwei and Feng, Yuqi and Sun, Yanan}, title = {Towards Accurate and Robust Architectures via Neural Architecture Search}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5967-5976} }
Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaption: Buzhen Huang,

Chen Li,

Chongyang Xu,

Liang Pan,

Yangang Wang,

Gim Hee Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2024_CVPR, author = {Huang, Buzhen and Li, Chen and Xu, Chongyang and Pan, Liang and Wang, Yangang and Lee, Gim Hee}, title = {Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaption}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1011-1021} }
Taming Stable Diffusion for Text to 360 Panorama Image Generation: Cheng Zhang,

Qianyi Wu,

Camilo Cruz Gambardella,

Xiaoshui Huang,

Dinh Phung,

Wanli Ouyang,

Jianfei Cai; [pdf] [supp]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Cheng and Wu, Qianyi and Gambardella, Camilo Cruz and Huang, Xiaoshui and Phung, Dinh and Ouyang, Wanli and Cai, Jianfei}, title = {Taming Stable Diffusion for Text to 360 Panorama Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6347-6357} }
Modular Blind Video Quality Assessment: Wen Wen,

Mu Li,

Yabin Zhang,

Yiting Liao,

Junlin Li,

Li Zhang,

Kede Ma; [pdf] [arXiv]
[bibtex]
@InProceedings{Wen_2024_CVPR, author = {Wen, Wen and Li, Mu and Zhang, Yabin and Liao, Yiting and Li, Junlin and Zhang, Li and Ma, Kede}, title = {Modular Blind Video Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2763-2772} }
RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method: Ming Yan,

Yan Zhang,

Shuqiang Cai,

Shuqi Fan,

Xincheng Lin,

Yudi Dai,

Siqi Shen,

Chenglu Wen,

Lan Xu,

Yuexin Ma,

Cheng Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yan_2024_CVPR, author = {Yan, Ming and Zhang, Yan and Cai, Shuqiang and Fan, Shuqi and Lin, Xincheng and Dai, Yudi and Shen, Siqi and Wen, Chenglu and Xu, Lan and Ma, Yuexin and Wang, Cheng}, title = {RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2250-2262} }
One-Class Face Anti-spoofing via Spoof Cue Map-Guided Feature Learning: Pei-Kai Huang,

Cheng-Hsuan Chiang,

Tzu-Hsien Chen,

Jun-Xiong Chong,

Tyng-Luh Liu,

Chiou-Ting Hsu; [pdf]
[bibtex]
@InProceedings{Huang_2024_CVPR, author = {Huang, Pei-Kai and Chiang, Cheng-Hsuan and Chen, Tzu-Hsien and Chong, Jun-Xiong and Liu, Tyng-Luh and Hsu, Chiou-Ting}, title = {One-Class Face Anti-spoofing via Spoof Cue Map-Guided Feature Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {277-286} }
InteractDiffusion: Interaction Control in Text-to-Image Diffusion Models: Jiun Tian Hoe,

Xudong Jiang,

Chee Seng Chan,

Yap-Peng Tan,

Weipeng Hu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hoe_2024_CVPR, author = {Hoe, Jiun Tian and Jiang, Xudong and Chan, Chee Seng and Tan, Yap-Peng and Hu, Weipeng}, title = {InteractDiffusion: Interaction Control in Text-to-Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6180-6189} }
Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models: Jiayun Luo,

Siddhesh Khandelwal,

Leonid Sigal,

Boyang Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Luo_2024_CVPR, author = {Luo, Jiayun and Khandelwal, Siddhesh and Sigal, Leonid and Li, Boyang}, title = {Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4029-4040} }
SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation: Vinkle Srivastav,

Keqi Chen,

Nicolas Padoy; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Srivastav_2024_CVPR, author = {Srivastav, Vinkle and Chen, Keqi and Padoy, Nicolas}, title = {SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2502-2512} }
Joint2Human: High-Quality 3D Human Generation via Compact Spherical Embedding of 3D Joints: Muxin Zhang,

Qiao Feng,

Zhuo Su,

Chao Wen,

Zhou Xue,

Kun Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Muxin and Feng, Qiao and Su, Zhuo and Wen, Chao and Xue, Zhou and Li, Kun}, title = {Joint2Human: High-Quality 3D Human Generation via Compact Spherical Embedding of 3D Joints}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1429-1438} }
Prompt-Free Diffusion: Taking "Text" out of Text-to-Image Diffusion Models: Xingqian Xu,

Jiayi Guo,

Zhangyang Wang,

Gao Huang,

Irfan Essa,

Humphrey Shi; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xu_2024_CVPR, author = {Xu, Xingqian and Guo, Jiayi and Wang, Zhangyang and Huang, Gao and Essa, Irfan and Shi, Humphrey}, title = {Prompt-Free Diffusion: Taking ''Text'' out of Text-to-Image Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8682-8692} }
Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning: Jaewoo Jeong,

Daehee Park,

Kuk-Jin Yoon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jeong_2024_CVPR, author = {Jeong, Jaewoo and Park, Daehee and Yoon, Kuk-Jin}, title = {Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1617-1628} }
CLOAF: CoLlisiOn-Aware Human Flow: Andrey Davydov,

Martin Engilberge,

Mathieu Salzmann,

Pascal Fua; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Davydov_2024_CVPR, author = {Davydov, Andrey and Engilberge, Martin and Salzmann, Mathieu and Fua, Pascal}, title = {CLOAF: CoLlisiOn-Aware Human Flow}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1176-1185} }
Hybrid Functional Maps for Crease-Aware Non-Isometric Shape Matching: Lennart Bastian,

Yizheng Xie,

Nassir Navab,

Zorah Lähner; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bastian_2024_CVPR, author = {Bastian, Lennart and Xie, Yizheng and Navab, Nassir and L\"ahner, Zorah}, title = {Hybrid Functional Maps for Crease-Aware Non-Isometric Shape Matching}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3313-3323} }
Density-Guided Semi-Supervised 3D Semantic Segmentation with Dual-Space Hardness Sampling: Jianan Li,

Qiulei Dong; [pdf] [supp]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Jianan and Dong, Qiulei}, title = {Density-Guided Semi-Supervised 3D Semantic Segmentation with Dual-Space Hardness Sampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3260-3269} }
ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separation: Moayed Haji-Ali,

Guha Balakrishnan,

Vicente Ordonez; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Haji-Ali_2024_CVPR, author = {Haji-Ali, Moayed and Balakrishnan, Guha and Ordonez, Vicente}, title = {ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6603-6612} }
Locally Adaptive Neural 3D Morphable Models: Michail Tarasiou,

Rolandos Alexandros Potamias,

Eimear O'Sullivan,

Stylianos Ploumpis,

Stefanos Zafeiriou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Tarasiou_2024_CVPR, author = {Tarasiou, Michail and Potamias, Rolandos Alexandros and O'Sullivan, Eimear and Ploumpis, Stylianos and Zafeiriou, Stefanos}, title = {Locally Adaptive Neural 3D Morphable Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1867-1876} }
ICON: Incremental CONfidence for Joint Pose and Radiance Field Optimization: Weiyao Wang,

Pierre Gleize,

Hao Tang,

Xingyu Chen,

Kevin J Liang,

Matt Feiszli; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Weiyao and Gleize, Pierre and Tang, Hao and Chen, Xingyu and Liang, Kevin J and Feiszli, Matt}, title = {ICON: Incremental CONfidence for Joint Pose and Radiance Field Optimization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5406-5417} }
Learned Scanpaths Aid Blind Panoramic Video Quality Assessment: Kanglong Fan,

Wen Wen,

Mu Li,

Yifan Peng,

Kede Ma; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fan_2024_CVPR, author = {Fan, Kanglong and Wen, Wen and Li, Mu and Peng, Yifan and Ma, Kede}, title = {Learned Scanpaths Aid Blind Panoramic Video Quality Assessment}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2599-2608} }
TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models: Haomiao Ni,

Bernhard Egger,

Suhas Lohit,

Anoop Cherian,

Ye Wang,

Toshiaki Koike-Akino,

Sharon X. Huang,

Tim K. Marks; [pdf] [supp]
[bibtex]
@InProceedings{Ni_2024_CVPR, author = {Ni, Haomiao and Egger, Bernhard and Lohit, Suhas and Cherian, Anoop and Wang, Ye and Koike-Akino, Toshiaki and Huang, Sharon X. and Marks, Tim K.}, title = {TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9015-9025} }
iToF-flow-based High Frame Rate Depth Imaging: Yu Meng,

Zhou Xue,

Xu Chang,

Xuemei Hu,

Tao Yue; [pdf]
[bibtex]
@InProceedings{Meng_2024_CVPR, author = {Meng, Yu and Xue, Zhou and Chang, Xu and Hu, Xuemei and Yue, Tao}, title = {iToF-flow-based High Frame Rate Depth Imaging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4929-4938} }
Relightful Harmonization: Lighting-aware Portrait Background Replacement: Mengwei Ren,

Wei Xiong,

Jae Shin Yoon,

Zhixin Shu,

Jianming Zhang,

HyunJoon Jung,

Guido Gerig,

He Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ren_2024_CVPR, author = {Ren, Mengwei and Xiong, Wei and Yoon, Jae Shin and Shu, Zhixin and Zhang, Jianming and Jung, HyunJoon and Gerig, Guido and Zhang, He}, title = {Relightful Harmonization: Lighting-aware Portrait Background Replacement}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6452-6462} }
Mitigating Motion Blur in Neural Radiance Fields with Events and Frames: Marco Cannici,

Davide Scaramuzza; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cannici_2024_CVPR, author = {Cannici, Marco and Scaramuzza, Davide}, title = {Mitigating Motion Blur in Neural Radiance Fields with Events and Frames}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9286-9296} }
TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation: Sai Kumar Dwivedi,

Yu Sun,

Priyanka Patel,

Yao Feng,

Michael J. Black; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dwivedi_2024_CVPR, author = {Dwivedi, Sai Kumar and Sun, Yu and Patel, Priyanka and Feng, Yao and Black, Michael J.}, title = {TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1323-1333} }
FaceCom: Towards High-fidelity 3D Facial Shape Completion via Optimization and Inpainting Guidance: Yinglong Li,

Hongyu Wu,

Xiaogang Wang,

Qingzhao Qin,

Yijiao Zhao,

Yong Wang,

Aimin Hao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Yinglong and Wu, Hongyu and Wang, Xiaogang and Qin, Qingzhao and Zhao, Yijiao and Wang, Yong and Hao, Aimin}, title = {FaceCom: Towards High-fidelity 3D Facial Shape Completion via Optimization and Inpainting Guidance}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2177-2186} }
LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting Estimation: Xuecan Wang,

Shibang Xiao,

Xiaohui Liang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Xuecan and Xiao, Shibang and Liang, Xiaohui}, title = {LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4536-4545} }
FaceLift: Semi-supervised 3D Facial Landmark Localization: David Ferman,

Pablo Garrido,

Gaurav Bharaj; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ferman_2024_CVPR, author = {Ferman, David and Garrido, Pablo and Bharaj, Gaurav}, title = {FaceLift: Semi-supervised 3D Facial Landmark Localization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1781-1791} }
PSDPM: Prototype-based Secondary Discriminative Pixels Mining for Weakly Supervised Semantic Segmentation: Xinqiao Zhao,

Ziqian Yang,

Tianhong Dai,

Bingfeng Zhang,

Jimin Xiao; [pdf]
[bibtex]
@InProceedings{Zhao_2024_CVPR, author = {Zhao, Xinqiao and Yang, Ziqian and Dai, Tianhong and Zhang, Bingfeng and Xiao, Jimin}, title = {PSDPM: Prototype-based Secondary Discriminative Pixels Mining for Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3437-3446} }
Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentation: Bingfeng Zhang,

Siyue Yu,

Yunchao Wei,

Yao Zhao,

Jimin Xiao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Bingfeng and Yu, Siyue and Wei, Yunchao and Zhao, Yao and Xiao, Jimin}, title = {Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3796-3806} }
LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition: Zhonglin Sun,

Chen Feng,

Ioannis Patras,

Georgios Tzimiropoulos; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2024_CVPR, author = {Sun, Zhonglin and Feng, Chen and Patras, Ioannis and Tzimiropoulos, Georgios}, title = {LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1639-1649} }
SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation: Bin Xie,

Jiale Cao,

Jin Xie,

Fahad Shahbaz Khan,

Yanwei Pang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xie_2024_CVPR, author = {Xie, Bin and Cao, Jiale and Xie, Jin and Khan, Fahad Shahbaz and Pang, Yanwei}, title = {SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3426-3436} }
GPLD3D: Latent Diffusion of 3D Shape Generative Models by Enforcing Geometric and Physical Priors: Yuan Dong,

Qi Zuo,

Xiaodong Gu,

Weihao Yuan,

Zhengyi Zhao,

Zilong Dong,

Liefeng Bo,

Qixing Huang; [pdf] [supp]
[bibtex]
@InProceedings{Dong_2024_CVPR, author = {Dong, Yuan and Zuo, Qi and Gu, Xiaodong and Yuan, Weihao and Zhao, Zhengyi and Dong, Zilong and Bo, Liefeng and Huang, Qixing}, title = {GPLD3D: Latent Diffusion of 3D Shape Generative Models by Enforcing Geometric and Physical Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {56-66} }
Self-correcting LLM-controlled Diffusion Models: Tsung-Han Wu,

Long Lian,

Joseph E. Gonzalez,

Boyi Li,

Trevor Darrell; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2024_CVPR, author = {Wu, Tsung-Han and Lian, Long and Gonzalez, Joseph E. and Li, Boyi and Darrell, Trevor}, title = {Self-correcting LLM-controlled Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6327-6336} }
PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios: Jingbo Wang,

Zhengyi Luo,

Ye Yuan,

Yixuan Li,

Bo Dai; [pdf] [supp]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Jingbo and Luo, Zhengyi and Yuan, Ye and Li, Yixuan and Dai, Bo}, title = {PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {718-728} }
LTM: Lightweight Textured Mesh Extraction and Refinement of Large Unbounded Scenes for Efficient Storage and Real-time Rendering: Jaehoon Choi,

Rajvi Shah,

Qinbo Li,

Yipeng Wang,

Ayush Saraf,

Changil Kim,

Jia-Bin Huang,

Dinesh Manocha,

Suhib Alsisan,

Johannes Kopf; [pdf] [supp]
[bibtex]
@InProceedings{Choi_2024_CVPR, author = {Choi, Jaehoon and Shah, Rajvi and Li, Qinbo and Wang, Yipeng and Saraf, Ayush and Kim, Changil and Huang, Jia-Bin and Manocha, Dinesh and Alsisan, Suhib and Kopf, Johannes}, title = {LTM: Lightweight Textured Mesh Extraction and Refinement of Large Unbounded Scenes for Efficient Storage and Real-time Rendering}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5053-5063} }
Don't Drop Your Samples! Coherence-Aware Training Benefits Conditional Diffusion: Nicolas Dufour,

Victor Besnier,

Vicky Kalogeiton,

David Picard; [pdf] [supp]
[bibtex]
@InProceedings{Dufour_2024_CVPR, author = {Dufour, Nicolas and Besnier, Victor and Kalogeiton, Vicky and Picard, David}, title = {Don't Drop Your Samples! Coherence-Aware Training Benefits Conditional Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6264-6273} }
What Do You See in Vehicle? Comprehensive Vision Solution for In-Vehicle Gaze Estimation: Yihua Cheng,

Yaning Zhu,

Zongji Wang,

Hongquan Hao,

Yongwei Liu,

Shiqing Cheng,

Xi Wang,

Hyung Jin Chang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2024_CVPR, author = {Cheng, Yihua and Zhu, Yaning and Wang, Zongji and Hao, Hongquan and Liu, Yongwei and Cheng, Shiqing and Wang, Xi and Chang, Hyung Jin}, title = {What Do You See in Vehicle? Comprehensive Vision Solution for In-Vehicle Gaze Estimation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1556-1565} }
UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and Unfavorable Sets: Youngju Na,

Woo Jae Kim,

Kyu Beom Han,

Suhyeon Ha,

Sung-Eui Yoon; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Na_2024_CVPR, author = {Na, Youngju and Kim, Woo Jae and Han, Kyu Beom and Ha, Suhyeon and Yoon, Sung-Eui}, title = {UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and Unfavorable Sets}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5094-5104} }
Breathing Life Into Sketches Using Text-to-Video Priors: Rinon Gal,

Yael Vinker,

Yuval Alaluf,

Amit Bermano,

Daniel Cohen-Or,

Ariel Shamir,

Gal Chechik; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Gal_2024_CVPR, author = {Gal, Rinon and Vinker, Yael and Alaluf, Yuval and Bermano, Amit and Cohen-Or, Daniel and Shamir, Ariel and Chechik, Gal}, title = {Breathing Life Into Sketches Using Text-to-Video Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4325-4336} }
Learning Diffusion Texture Priors for Image Restoration: Tian Ye,

Sixiang Chen,

Wenhao Chai,

Zhaohu Xing,

Jing Qin,

Ge Lin,

Lei Zhu; [pdf]
[bibtex]
@InProceedings{Ye_2024_CVPR, author = {Ye, Tian and Chen, Sixiang and Chai, Wenhao and Xing, Zhaohu and Qin, Jing and Lin, Ge and Zhu, Lei}, title = {Learning Diffusion Texture Priors for Image Restoration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2524-2534} }
Entangled View-Epipolar Information Aggregation for Generalizable Neural Radiance Fields: Zhiyuan Min,

Yawei Luo,

Wei Yang,

Yuesong Wang,

Yi Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Min_2024_CVPR, author = {Min, Zhiyuan and Luo, Yawei and Yang, Wei and Wang, Yuesong and Yang, Yi}, title = {Entangled View-Epipolar Information Aggregation for Generalizable Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4906-4916} }
YolOOD: Utilizing Object Detection Concepts for Multi-Label Out-of-Distribution Detection: Alon Zolfi,

Guy Amit,

Amit Baras,

Satoru Koda,

Ikuya Morikawa,

Yuval Elovici,

Asaf Shabtai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zolfi_2024_CVPR, author = {Zolfi, Alon and Amit, Guy and Baras, Amit and Koda, Satoru and Morikawa, Ikuya and Elovici, Yuval and Shabtai, Asaf}, title = {YolOOD: Utilizing Object Detection Concepts for Multi-Label Out-of-Distribution Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5788-5797} }
Collaborating Foundation Models for Domain Generalized Semantic Segmentation: Yasser Benigmim,

Subhankar Roy,

Slim Essid,

Vicky Kalogeiton,

Stéphane Lathuilière; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Benigmim_2024_CVPR, author = {Benigmim, Yasser and Roy, Subhankar and Essid, Slim and Kalogeiton, Vicky and Lathuili\`ere, St\'ephane}, title = {Collaborating Foundation Models for Domain Generalized Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3108-3119} }
Towards Variable and Coordinated Holistic Co-Speech Motion Generation: Yifei Liu,

Qiong Cao,

Yandong Wen,

Huaiguang Jiang,

Changxing Ding; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Yifei and Cao, Qiong and Wen, Yandong and Jiang, Huaiguang and Ding, Changxing}, title = {Towards Variable and Coordinated Holistic Co-Speech Motion Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1566-1576} }
AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation: Haonan Wang,

Qixiang Zhang,

Yi Li,

Xiaomeng Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Haonan and Zhang, Qixiang and Li, Yi and Li, Xiaomeng}, title = {AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3627-3636} }
SIGNeRF: Scene Integrated Generation for Neural Radiance Fields: Jan-Niklas Dihlmann,

Andreas Engelhardt,

Hendrik Lensch; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dihlmann_2024_CVPR, author = {Dihlmann, Jan-Niklas and Engelhardt, Andreas and Lensch, Hendrik}, title = {SIGNeRF: Scene Integrated Generation for Neural Radiance Fields}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6679-6688} }
Generating Illustrated Instructions: Sachit Menon,

Ishan Misra,

Rohit Girdhar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Menon_2024_CVPR, author = {Menon, Sachit and Misra, Ishan and Girdhar, Rohit}, title = {Generating Illustrated Instructions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6274-6284} }
Robust Image Denoising through Adversarial Frequency Mixup: Donghun Ryou,

Inju Ha,

Hyewon Yoo,

Dongwan Kim,

Bohyung Han; [pdf] [supp]
[bibtex]
@InProceedings{Ryou_2024_CVPR, author = {Ryou, Donghun and Ha, Inju and Yoo, Hyewon and Kim, Dongwan and Han, Bohyung}, title = {Robust Image Denoising through Adversarial Frequency Mixup}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2723-2732} }
AnyScene: Customized Image Synthesis with Composited Foreground: Ruidong Chen,

Lanjun Wang,

Weizhi Nie,

Yongdong Zhang,

An-An Liu; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Ruidong and Wang, Lanjun and Nie, Weizhi and Zhang, Yongdong and Liu, An-An}, title = {AnyScene: Customized Image Synthesis with Composited Foreground}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8724-8733} }
Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts: Cansu Korkmaz,

A. Murat Tekalp,

Zafer Dogan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Korkmaz_2024_CVPR, author = {Korkmaz, Cansu and Tekalp, A. Murat and Dogan, Zafer}, title = {Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5926-5936} }
Monocular Identity-Conditioned Facial Reflectance Reconstruction: Xingyu Ren,

Jiankang Deng,

Yuhao Cheng,

Jia Guo,

Chao Ma,

Yichao Yan,

Wenhan Zhu,

Xiaokang Yang; [pdf] [arXiv]
[bibtex]
@InProceedings{Ren_2024_CVPR, author = {Ren, Xingyu and Deng, Jiankang and Cheng, Yuhao and Guo, Jia and Ma, Chao and Yan, Yichao and Zhu, Wenhan and Yang, Xiaokang}, title = {Monocular Identity-Conditioned Facial Reflectance Reconstruction}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {885-895} }
C3: High-Performance and Low-Complexity Neural Compression from a Single Image or Video: Hyunjik Kim,

Matthias Bauer,

Lucas Theis,

Jonathan Richard Schwarz,

Emilien Dupont; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_CVPR, author = {Kim, Hyunjik and Bauer, Matthias and Theis, Lucas and Schwarz, Jonathan Richard and Dupont, Emilien}, title = {C3: High-Performance and Low-Complexity Neural Compression from a Single Image or Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9347-9358} }
Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis: Zanlin Ni,

Yulin Wang,

Renping Zhou,

Jiayi Guo,

Jinyi Hu,

Zhiyuan Liu,

Shiji Song,

Yuan Yao,

Gao Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ni_2024_CVPR, author = {Ni, Zanlin and Wang, Yulin and Zhou, Renping and Guo, Jiayi and Hu, Jinyi and Liu, Zhiyuan and Song, Shiji and Yao, Yuan and Huang, Gao}, title = {Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7007-7016} }
ANIM: Accurate Neural Implicit Model for Human Reconstruction from a single RGB-D Image: Marco Pesavento,

Yuanlu Xu,

Nikolaos Sarafianos,

Robert Maier,

Ziyan Wang,

Chun-Han Yao,

Marco Volino,

Edmond Boyer,

Adrian Hilton,

Tony Tung; [pdf] [supp]
[bibtex]
@InProceedings{Pesavento_2024_CVPR, author = {Pesavento, Marco and Xu, Yuanlu and Sarafianos, Nikolaos and Maier, Robert and Wang, Ziyan and Yao, Chun-Han and Volino, Marco and Boyer, Edmond and Hilton, Adrian and Tung, Tony}, title = {ANIM: Accurate Neural Implicit Model for Human Reconstruction from a single RGB-D Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5448-5458} }
Real-Time Simulated Avatar from Head-Mounted Sensors: Zhengyi Luo,

Jinkun Cao,

Rawal Khirodkar,

Alexander Winkler,

Kris Kitani,

Weipeng Xu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Luo_2024_CVPR, author = {Luo, Zhengyi and Cao, Jinkun and Khirodkar, Rawal and Winkler, Alexander and Kitani, Kris and Xu, Weipeng}, title = {Real-Time Simulated Avatar from Head-Mounted Sensors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {571-581} }
Seamless Human Motion Composition with Blended Positional Encodings: German Barquero,

Sergio Escalera,

Cristina Palmero; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Barquero_2024_CVPR, author = {Barquero, German and Escalera, Sergio and Palmero, Cristina}, title = {Seamless Human Motion Composition with Blended Positional Encodings}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {457-469} }
FedUV: Uniformity and Variance for Heterogeneous Federated Learning: Ha Min Son,

Moon-Hyun Kim,

Tai-Myoung Chung,

Chao Huang,

Xin Liu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Son_2024_CVPR, author = {Son, Ha Min and Kim, Moon-Hyun and Chung, Tai-Myoung and Huang, Chao and Liu, Xin}, title = {FedUV: Uniformity and Variance for Heterogeneous Federated Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5863-5872} }
GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning: Ye Yuan,

Xueting Li,

Yangyi Huang,

Shalini De Mello,

Koki Nagano,

Jan Kautz,

Umar Iqbal; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yuan_2024_CVPR, author = {Yuan, Ye and Li, Xueting and Huang, Yangyi and De Mello, Shalini and Nagano, Koki and Kautz, Jan and Iqbal, Umar}, title = {GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {896-905} }
Grounding Everything: Emerging Localization Properties in Vision-Language Transformers: Walid Bousselham,

Felix Petersen,

Vittorio Ferrari,

Hilde Kuehne; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bousselham_2024_CVPR, author = {Bousselham, Walid and Petersen, Felix and Ferrari, Vittorio and Kuehne, Hilde}, title = {Grounding Everything: Emerging Localization Properties in Vision-Language Transformers}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3828-3837} }
Mean-Shift Feature Transformer: Takumi Kobayashi; [pdf] [supp]
[bibtex]
@InProceedings{Kobayashi_2024_CVPR, author = {Kobayashi, Takumi}, title = {Mean-Shift Feature Transformer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6047-6056} }
Domain Separation Graph Neural Networks for Saliency Object Ranking: Zijian Wu,

Jun Lu,

Jing Han,

Lianfa Bai,

Yi Zhang,

Zhuang Zhao,

Siyang Song; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2024_CVPR, author = {Wu, Zijian and Lu, Jun and Han, Jing and Bai, Lianfa and Zhang, Yi and Zhao, Zhuang and Song, Siyang}, title = {Domain Separation Graph Neural Networks for Saliency Object Ranking}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3964-3974} }
RAM-Avatar: Real-time Photo-Realistic Avatar from Monocular Videos with Full-body Control: Xiang Deng,

Zerong Zheng,

Yuxiang Zhang,

Jingxiang Sun,

Chao Xu,

Xiaodong Yang,

Lizhen Wang,

Yebin Liu; [pdf] [supp]
[bibtex]
@InProceedings{Deng_2024_CVPR, author = {Deng, Xiang and Zheng, Zerong and Zhang, Yuxiang and Sun, Jingxiang and Xu, Chao and Yang, Xiaodong and Wang, Lizhen and Liu, Yebin}, title = {RAM-Avatar: Real-time Photo-Realistic Avatar from Monocular Videos with Full-body Control}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1996-2007} }
Video Prediction by Modeling Videos as Continuous Multi-Dimensional Processes: Gaurav Shrivastava,

Abhinav Shrivastava; [pdf] [supp]
[bibtex]
@InProceedings{Shrivastava_2024_CVPR, author = {Shrivastava, Gaurav and Shrivastava, Abhinav}, title = {Video Prediction by Modeling Videos as Continuous Multi-Dimensional Processes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7236-7245} }
PICTURE: PhotorealistIC virtual Try-on from UnconstRained dEsigns: Shuliang Ning,

Duomin Wang,

Yipeng Qin,

Zirong Jin,

Baoyuan Wang,

Xiaoguang Han; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ning_2024_CVPR, author = {Ning, Shuliang and Wang, Duomin and Qin, Yipeng and Jin, Zirong and Wang, Baoyuan and Han, Xiaoguang}, title = {PICTURE: PhotorealistIC virtual Try-on from UnconstRained dEsigns}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6976-6985} }
Towards Robust 3D Pose Transfer with Adversarial Learning: Haoyu Chen,

Hao Tang,

Ehsan Adeli,

Guoying Zhao; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Haoyu and Tang, Hao and Adeli, Ehsan and Zhao, Guoying}, title = {Towards Robust 3D Pose Transfer with Adversarial Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2295-2304} }
EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation: Chanyoung Kim,

Woojung Han,

Dayun Ju,

Seong Jae Hwang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_CVPR, author = {Kim, Chanyoung and Han, Woojung and Ju, Dayun and Hwang, Seong Jae}, title = {EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3523-3533} }
AVID: Any-Length Video Inpainting with Diffusion Model: Zhixing Zhang,

Bichen Wu,

Xiaoyan Wang,

Yaqiao Luo,

Luxin Zhang,

Yinan Zhao,

Peter Vajda,

Dimitris Metaxas,

Licheng Yu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Zhixing and Wu, Bichen and Wang, Xiaoyan and Luo, Yaqiao and Zhang, Luxin and Zhao, Yinan and Vajda, Peter and Metaxas, Dimitris and Yu, Licheng}, title = {AVID: Any-Length Video Inpainting with Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7162-7172} }
NoiseCollage: A Layout-Aware Text-to-Image Diffusion Model Based on Noise Cropping and Merging: Takahiro Shirakawa,

Seiichi Uchida; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shirakawa_2024_CVPR, author = {Shirakawa, Takahiro and Uchida, Seiichi}, title = {NoiseCollage: A Layout-Aware Text-to-Image Diffusion Model Based on Noise Cropping and Merging}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8921-8930} }
Arbitrary Motion Style Transfer with Multi-condition Motion Latent Diffusion Model: Wenfeng Song,

Xingliang Jin,

Shuai Li,

Chenglizhao Chen,

Aimin Hao,

Xia Hou,

Ning Li,

Hong Qin; [pdf] [supp]
[bibtex]
@InProceedings{Song_2024_CVPR, author = {Song, Wenfeng and Jin, Xingliang and Li, Shuai and Chen, Chenglizhao and Hao, Aimin and Hou, Xia and Li, Ning and Qin, Hong}, title = {Arbitrary Motion Style Transfer with Multi-condition Motion Latent Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {821-830} }
ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions: Chunlong Xia,

Xinliang Wang,

Feng Lv,

Xin Hao,

Yifeng Shi; [pdf]
[bibtex]
@InProceedings{Xia_2024_CVPR, author = {Xia, Chunlong and Wang, Xinliang and Lv, Feng and Hao, Xin and Shi, Yifeng}, title = {ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5493-5502} }
PromptCoT: Align Prompt Distribution via Adapted Chain-of-Thought: Junyi Yao,

Yijiang Liu,

Zhen Dong,

Mingfei Guo,

Helan Hu,

Kurt Keutzer,

Li Du,

Daquan Zhou,

Shanghang Zhang; [pdf] [supp]
[bibtex]
@InProceedings{Yao_2024_CVPR, author = {Yao, Junyi and Liu, Yijiang and Dong, Zhen and Guo, Mingfei and Hu, Helan and Keutzer, Kurt and Du, Li and Zhou, Daquan and Zhang, Shanghang}, title = {PromptCoT: Align Prompt Distribution via Adapted Chain-of-Thought}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7027-7037} }
Anomaly Score: Evaluating Generative Models and Individual Generated Images based on Complexity and Vulnerability: Jaehui Hwang,

Junghyuk Lee,

Jong-Seok Lee; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hwang_2024_CVPR, author = {Hwang, Jaehui and Lee, Junghyuk and Lee, Jong-Seok}, title = {Anomaly Score: Evaluating Generative Models and Individual Generated Images based on Complexity and Vulnerability}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8754-8763} }
GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image: Chong Bao,

Yinda Zhang,

Yuan Li,

Xiyu Zhang,

Bangbang Yang,

Hujun Bao,

Marc Pollefeys,

Guofeng Zhang,

Zhaopeng Cui; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bao_2024_CVPR, author = {Bao, Chong and Zhang, Yinda and Li, Yuan and Zhang, Xiyu and Yang, Bangbang and Bao, Hujun and Pollefeys, Marc and Zhang, Guofeng and Cui, Zhaopeng}, title = {GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8952-8963} }
Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation: Jingyun Wang,

Guoliang Kang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Jingyun and Kang, Guoliang}, title = {Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4102-4112} }
Unlocking Pre-trained Image Backbones for Semantic Image Synthesis: Tariq Berrada Ifriqi,

Jakob Verbeek,

Camille Couprie,

Karteek Alahari; [pdf] [supp]
[bibtex]
@InProceedings{Ifriqi_2024_CVPR, author = {Ifriqi, Tariq Berrada and Verbeek, Jakob and Couprie, Camille and Alahari, Karteek}, title = {Unlocking Pre-trained Image Backbones for Semantic Image Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7840-7849} }
TexTile: A Differentiable Metric for Texture Tileability: Carlos Rodriguez-Pardo,

Dan Casas,

Elena Garces,

Jorge Lopez-Moreno; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rodriguez-Pardo_2024_CVPR, author = {Rodriguez-Pardo, Carlos and Casas, Dan and Garces, Elena and Lopez-Moreno, Jorge}, title = {TexTile: A Differentiable Metric for Texture Tileability}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4439-4449} }
Improving Image Restoration through Removing Degradations in Textual Representations: Jingbo Lin,

Zhilu Zhang,

Yuxiang Wei,

Dongwei Ren,

Dongsheng Jiang,

Qi Tian,

Wangmeng Zuo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lin_2024_CVPR, author = {Lin, Jingbo and Zhang, Zhilu and Wei, Yuxiang and Ren, Dongwei and Jiang, Dongsheng and Tian, Qi and Zuo, Wangmeng}, title = {Improving Image Restoration through Removing Degradations in Textual Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2866-2878} }
ZONE: Zero-Shot Instruction-Guided Local Editing: Shanglin Li,

Bohan Zeng,

Yutang Feng,

Sicheng Gao,

Xiuhui Liu,

Jiaming Liu,

Lin Li,

Xu Tang,

Yao Hu,

Jianzhuang Liu,

Baochang Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Shanglin and Zeng, Bohan and Feng, Yutang and Gao, Sicheng and Liu, Xiuhui and Liu, Jiaming and Li, Lin and Tang, Xu and Hu, Yao and Liu, Jianzhuang and Zhang, Baochang}, title = {ZONE: Zero-Shot Instruction-Guided Local Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6254-6263} }
U-VAP: User-specified Visual Appearance Personalization via Decoupled Self Augmentation: You Wu,

Kean Liu,

Xiaoyue Mi,

Fan Tang,

Juan Cao,

Jintao Li; [pdf] [supp]
[bibtex]
@InProceedings{Wu_2024_CVPR, author = {Wu, You and Liu, Kean and Mi, Xiaoyue and Tang, Fan and Cao, Juan and Li, Jintao}, title = {U-VAP: User-specified Visual Appearance Personalization via Decoupled Self Augmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9482-9491} }
HHMR: Holistic Hand Mesh Recovery by Enhancing the Multimodal Controllability of Graph Diffusion Models: Mengcheng Li,

Hongwen Zhang,

Yuxiang Zhang,

Ruizhi Shao,

Tao Yu,

Yebin Liu; [pdf] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Mengcheng and Zhang, Hongwen and Zhang, Yuxiang and Shao, Ruizhi and Yu, Tao and Liu, Yebin}, title = {HHMR: Holistic Hand Mesh Recovery by Enhancing the Multimodal Controllability of Graph Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {645-654} }
Robust Self-calibration of Focal Lengths from the Fundamental Matrix: Viktor Kocur,

Daniel Kyselica,

Zuzana Kukelova; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kocur_2024_CVPR, author = {Kocur, Viktor and Kyselica, Daniel and Kukelova, Zuzana}, title = {Robust Self-calibration of Focal Lengths from the Fundamental Matrix}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5220-5229} }
PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation: Ardian Umam,

Cheng-Kun Yang,

Min-Hung Chen,

Jen-Hui Chuang,

Yen-Yu Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Umam_2024_CVPR, author = {Umam, Ardian and Yang, Cheng-Kun and Chen, Min-Hung and Chuang, Jen-Hui and Lin, Yen-Yu}, title = {PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3470-3479} }
DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing: Yujun Shi,

Chuhui Xue,

Jun Hao Liew,

Jiachun Pan,

Hanshu Yan,

Wenqing Zhang,

Vincent Y. F. Tan,

Song Bai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shi_2024_CVPR, author = {Shi, Yujun and Xue, Chuhui and Liew, Jun Hao and Pan, Jiachun and Yan, Hanshu and Zhang, Wenqing and Tan, Vincent Y. F. and Bai, Song}, title = {DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8839-8849} }
Addressing Background Context Bias in Few-Shot Segmentation through Iterative Modulation: Lanyun Zhu,

Tianrun Chen,

Jianxiong Yin,

Simon See,

Jun Liu; [pdf] [supp]
[bibtex]
@InProceedings{Zhu_2024_CVPR, author = {Zhu, Lanyun and Chen, Tianrun and Yin, Jianxiong and See, Simon and Liu, Jun}, title = {Addressing Background Context Bias in Few-Shot Segmentation through Iterative Modulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3370-3379} }
TiNO-Edit: Timestep and Noise Optimization for Robust Diffusion-Based Image Editing: Sherry X Chen,

Yaron Vaxman,

Elad Ben Baruch,

David Asulin,

Aviad Moreshet,

Kuo-Chin Lien,

Misha Sra,

Pradeep Sen; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Sherry X and Vaxman, Yaron and Ben Baruch, Elad and Asulin, David and Moreshet, Aviad and Lien, Kuo-Chin and Sra, Misha and Sen, Pradeep}, title = {TiNO-Edit: Timestep and Noise Optimization for Robust Diffusion-Based Image Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6337-6346} }
AdaShift: Learning Discriminative Self-Gated Neural Feature Activation With an Adaptive Shift Factor: Sudong Cai; [pdf] [supp]
[bibtex]
@InProceedings{Cai_2024_CVPR, author = {Cai, Sudong}, title = {AdaShift: Learning Discriminative Self-Gated Neural Feature Activation With an Adaptive Shift Factor}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5947-5956} }
SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing: Zeyinzi Jiang,

Chaojie Mao,

Yulin Pan,

Zhen Han,

Jingfeng Zhang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2024_CVPR, author = {Jiang, Zeyinzi and Mao, Chaojie and Pan, Yulin and Han, Zhen and Zhang, Jingfeng}, title = {SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8995-9004} }
BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model: Yiran Song,

Qianyu Zhou,

Xiangtai Li,

Deng-Ping Fan,

Xuequan Lu,

Lizhuang Ma; [pdf] [supp]
[bibtex]
@InProceedings{Song_2024_CVPR, author = {Song, Yiran and Zhou, Qianyu and Li, Xiangtai and Fan, Deng-Ping and Lu, Xuequan and Ma, Lizhuang}, title = {BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3162-3173} }
Deciphering 'What' and 'Where' Visual Pathways from Spectral Clustering of Layer-Distributed Neural Representations: Xiao Zhang,

David Yunis,

Michael Maire; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Xiao and Yunis, David and Maire, Michael}, title = {Deciphering 'What' and 'Where' Visual Pathways from Spectral Clustering of Layer-Distributed Neural Representations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {4165-4175} }
Real-Time Exposure Correction via Collaborative Transformations and Adaptive Sampling: Ziwen Li,

Feng Zhang,

Meng Cao,

Jinpu Zhang,

Yuanjie Shao,

Yuehuan Wang,

Nong Sang; [pdf] [supp]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Ziwen and Zhang, Feng and Cao, Meng and Zhang, Jinpu and Shao, Yuanjie and Wang, Yuehuan and Sang, Nong}, title = {Real-Time Exposure Correction via Collaborative Transformations and Adaptive Sampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2984-2994} }
Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives: Ronghui Li,

YuXiang Zhang,

Yachao Zhang,

Hongwen Zhang,

Jie Guo,

Yan Zhang,

Yebin Liu,

Xiu Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Ronghui and Zhang, YuXiang and Zhang, Yachao and Zhang, Hongwen and Guo, Jie and Zhang, Yan and Liu, Yebin and Li, Xiu}, title = {Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1524-1534} }
Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection: Zhiyuan Yan,

Yuhao Luo,

Siwei Lyu,

Qingshan Liu,

Baoyuan Wu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yan_2024_CVPR, author = {Yan, Zhiyuan and Luo, Yuhao and Lyu, Siwei and Liu, Qingshan and Wu, Baoyuan}, title = {Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8984-8994} }
Scaling Laws of Synthetic Images for Model Training ... for Now: Lijie Fan,

Kaifeng Chen,

Dilip Krishnan,

Dina Katabi,

Phillip Isola,

Yonglong Tian; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fan_2024_CVPR, author = {Fan, Lijie and Chen, Kaifeng and Krishnan, Dilip and Katabi, Dina and Isola, Phillip and Tian, Yonglong}, title = {Scaling Laws of Synthetic Images for Model Training ... for Now}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7382-7392} }
State Space Models for Event Cameras: Nikola Zubic,

Mathias Gehrig,

Davide Scaramuzza; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zubic_2024_CVPR, author = {Zubic, Nikola and Gehrig, Mathias and Scaramuzza, Davide}, title = {State Space Models for Event Cameras}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5819-5828} }
TeTriRF: Temporal Tri-Plane Radiance Fields for Efficient Free-Viewpoint Video: Minye Wu,

Zehao Wang,

Georgios Kouros,

Tinne Tuytelaars; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2024_CVPR, author = {Wu, Minye and Wang, Zehao and Kouros, Georgios and Tuytelaars, Tinne}, title = {TeTriRF: Temporal Tri-Plane Radiance Fields for Efficient Free-Viewpoint Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6487-6496} }
Event-assisted Low-Light Video Object Segmentation: Hebei Li,

Jin Wang,

Jiahui Yuan,

Yue Li,

Wenming Weng,

Yansong Peng,

Yueyi Zhang,

Zhiwei Xiong,

Xiaoyan Sun; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Hebei and Wang, Jin and Yuan, Jiahui and Li, Yue and Weng, Wenming and Peng, Yansong and Zhang, Yueyi and Xiong, Zhiwei and Sun, Xiaoyan}, title = {Event-assisted Low-Light Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3250-3259} }
VidToMe: Video Token Merging for Zero-Shot Video Editing: Xirui Li,

Chao Ma,

Xiaokang Yang,

Ming-Hsuan Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Xirui and Ma, Chao and Yang, Xiaokang and Yang, Ming-Hsuan}, title = {VidToMe: Video Token Merging for Zero-Shot Video Editing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7486-7495} }
FaceChain-SuDe: Building Derived Class to Inherit Category Attributes for One-shot Subject-Driven Generation: Pengchong Qiao,

Lei Shang,

Chang Liu,

Baigui Sun,

Xiangyang Ji,

Jie Chen; [pdf] [supp]
[bibtex]
@InProceedings{Qiao_2024_CVPR, author = {Qiao, Pengchong and Shang, Lei and Liu, Chang and Sun, Baigui and Ji, Xiangyang and Chen, Jie}, title = {FaceChain-SuDe: Building Derived Class to Inherit Category Attributes for One-shot Subject-Driven Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7215-7224} }
StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On: Jeongho Kim,

Guojung Gu,

Minho Park,

Sunghyun Park,

Jaegul Choo; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kim_2024_CVPR, author = {Kim, Jeongho and Gu, Guojung and Park, Minho and Park, Sunghyun and Choo, Jaegul}, title = {StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8176-8185} }
Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Framework: Ziyao Huang,

Fan Tang,

Yong Zhang,

Xiaodong Cun,

Juan Cao,

Jintao Li,

Tong-Yee Lee; [pdf] [supp]
[bibtex]
@InProceedings{Huang_2024_CVPR, author = {Huang, Ziyao and Tang, Fan and Zhang, Yong and Cun, Xiaodong and Cao, Juan and Li, Jintao and Lee, Tong-Yee}, title = {Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Framework}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6997-7006} }
Learning Dynamic Tetrahedra for High-Quality Talking Head Synthesis: Zicheng Zhang,

Ruobing Zheng,

Bonan Li,

Congying Han,

Tianqi Li,

Meng Wang,

Tiande Guo,

Jingdong Chen,

Ziwen Liu,

Ming Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Zicheng and Zheng, Ruobing and Li, Bonan and Han, Congying and Li, Tianqi and Wang, Meng and Guo, Tiande and Chen, Jingdong and Liu, Ziwen and Yang, Ming}, title = {Learning Dynamic Tetrahedra for High-Quality Talking Head Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5209-5219} }
3D Geometry-Aware Deformable Gaussian Splatting for Dynamic View Synthesis: Zhicheng Lu,

Xiang Guo,

Le Hui,

Tianrui Chen,

Min Yang,

Xiao Tang,

Feng Zhu,

Yuchao Dai; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Lu_2024_CVPR, author = {Lu, Zhicheng and Guo, Xiang and Hui, Le and Chen, Tianrui and Yang, Min and Tang, Xiao and Zhu, Feng and Dai, Yuchao}, title = {3D Geometry-Aware Deformable Gaussian Splatting for Dynamic View Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8900-8910} }
Person-in-WiFi 3D: End-to-End Multi-Person 3D Pose Estimation with Wi-Fi: Kangwei Yan,

Fei Wang,

Bo Qian,

Han Ding,

Jinsong Han,

Xing Wei; [pdf]
[bibtex]
@InProceedings{Yan_2024_CVPR, author = {Yan, Kangwei and Wang, Fei and Qian, Bo and Ding, Han and Han, Jinsong and Wei, Xing}, title = {Person-in-WiFi 3D: End-to-End Multi-Person 3D Pose Estimation with Wi-Fi}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {969-978} }
Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis: Bichen Wu,

Ching-Yao Chuang,

Xiaoyan Wang,

Yichen Jia,

Kapil Krishnakumar,

Tong Xiao,

Feng Liang,

Licheng Yu,

Peter Vajda; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wu_2024_CVPR, author = {Wu, Bichen and Chuang, Ching-Yao and Wang, Xiaoyan and Jia, Yichen and Krishnakumar, Kapil and Xiao, Tong and Liang, Feng and Yu, Licheng and Vajda, Peter}, title = {Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8261-8270} }
SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models: Yuzhou Huang,

Liangbin Xie,

Xintao Wang,

Ziyang Yuan,

Xiaodong Cun,

Yixiao Ge,

Jiantao Zhou,

Chao Dong,

Rui Huang,

Ruimao Zhang,

Ying Shan; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Huang_2024_CVPR, author = {Huang, Yuzhou and Xie, Liangbin and Wang, Xintao and Yuan, Ziyang and Cun, Xiaodong and Ge, Yixiao and Zhou, Jiantao and Dong, Chao and Huang, Rui and Zhang, Ruimao and Shan, Ying}, title = {SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8362-8371} }
It's All About Your Sketch: Democratising Sketch Control in Diffusion Models: Subhadeep Koley,

Ayan Kumar Bhunia,

Deeptanshu Sekhri,

Aneeshan Sain,

Pinaki Nath Chowdhury,

Tao Xiang,

Yi-Zhe Song; [pdf] [supp]
[bibtex]
@InProceedings{Koley_2024_CVPR, author = {Koley, Subhadeep and Bhunia, Ayan Kumar and Sekhri, Deeptanshu and Sain, Aneeshan and Chowdhury, Pinaki Nath and Xiang, Tao and Song, Yi-Zhe}, title = {It's All About Your Sketch: Democratising Sketch Control in Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7204-7214} }
When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image Generation: Xiaoming Li,

Xinyu Hou,

Chen Change Loy; [pdf] [supp]
[bibtex]
@InProceedings{Li_2024_CVPR, author = {Li, Xiaoming and Hou, Xinyu and Loy, Chen Change}, title = {When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2187-2196} }
CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective: Shunsuke Yasuki,

Masato Taki; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yasuki_2024_CVPR, author = {Yasuki, Shunsuke and Taki, Masato}, title = {CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {341-351} }
Putting the Object Back into Video Object Segmentation: Ho Kei Cheng,

Seoung Wug Oh,

Brian Price,

Joon-Young Lee,

Alexander Schwing; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cheng_2024_CVPR, author = {Cheng, Ho Kei and Oh, Seoung Wug and Price, Brian and Lee, Joon-Young and Schwing, Alexander}, title = {Putting the Object Back into Video Object Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3151-3161} }
Concept Weaver: Enabling Multi-Concept Fusion in Text-to-Image Models: Gihyun Kwon,

Simon Jenni,

Dingzeyu Li,

Joon-Young Lee,

Jong Chul Ye,

Fabian Caba Heilbron; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kwon_2024_CVPR, author = {Kwon, Gihyun and Jenni, Simon and Li, Dingzeyu and Lee, Joon-Young and Ye, Jong Chul and Heilbron, Fabian Caba}, title = {Concept Weaver: Enabling Multi-Concept Fusion in Text-to-Image Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8880-8889} }
Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Mining: Jiahao Nie,

Yun Xing,

Gongjie Zhang,

Pei Yan,

Aoran Xiao,

Yap-Peng Tan,

Alex C. Kot,

Shijian Lu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Nie_2024_CVPR, author = {Nie, Jiahao and Xing, Yun and Zhang, Gongjie and Yan, Pei and Xiao, Aoran and Tan, Yap-Peng and Kot, Alex C. and Lu, Shijian}, title = {Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Mining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3380-3390} }
DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation: Junming Chen,

Yunfei Liu,

Jianan Wang,

Ailing Zeng,

Yu Li,

Qifeng Chen; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Junming and Liu, Yunfei and Wang, Jianan and Zeng, Ailing and Li, Yu and Chen, Qifeng}, title = {DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7352-7361} }
Animating General Image with Large Visual Motion Model: Dengsheng Chen,

Xiaoming Wei,

Xiaolin Wei; [pdf] [supp]
[bibtex]
@InProceedings{Chen_2024_CVPR, author = {Chen, Dengsheng and Wei, Xiaoming and Wei, Xiaolin}, title = {Animating General Image with Large Visual Motion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7131-7140} }
DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data: Qihao Liu,

Yi Zhang,

Song Bai,

Adam Kortylewski,

Alan Yuille; [pdf] [supp]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Qihao and Zhang, Yi and Bai, Song and Kortylewski, Adam and Yuille, Alan}, title = {DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6881-6891} }
OHTA: One-shot Hand Avatar via Data-driven Implicit Priors: Xiaozheng Zheng,

Chao Wen,

Zhuo Su,

Zeran Xu,

Zhaohu Li,

Yang Zhao,

Zhou Xue; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zheng_2024_CVPR, author = {Zheng, Xiaozheng and Wen, Chao and Su, Zhuo and Xu, Zeran and Li, Zhaohu and Zhao, Yang and Xue, Zhou}, title = {OHTA: One-shot Hand Avatar via Data-driven Implicit Priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {799-810} }
Human Motion Prediction Under Unexpected Perturbation: Jiangbei Yue,

Baiyi Li,

Julien Pettré,

Armin Seyfried,

He Wang; [pdf] [supp]
[bibtex]
@InProceedings{Yue_2024_CVPR, author = {Yue, Jiangbei and Li, Baiyi and Pettr\'e, Julien and Seyfried, Armin and Wang, He}, title = {Human Motion Prediction Under Unexpected Perturbation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1501-1511} }
Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors: Lihe Ding,

Shaocong Dong,

Zhanpeng Huang,

Zibin Wang,

Yiyuan Zhang,

Kaixiong Gong,

Dan Xu,

Tianfan Xue; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Ding_2024_CVPR, author = {Ding, Lihe and Dong, Shaocong and Huang, Zhanpeng and Wang, Zibin and Zhang, Yiyuan and Gong, Kaixiong and Xu, Dan and Xue, Tianfan}, title = {Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5115-5124} }
Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text: Junshu Tang,

Yanhong Zeng,

Ke Fan,

Xuheng Wang,

Bo Dai,

Kai Chen,

Lizhuang Ma; [pdf]
[bibtex]
@InProceedings{Tang_2024_CVPR, author = {Tang, Junshu and Zeng, Yanhong and Fan, Ke and Wang, Xuheng and Dai, Bo and Chen, Kai and Ma, Lizhuang}, title = {Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6243-6253} }
Neural Sign Actors: A Diffusion Model for 3D Sign Language Production from Text: Vasileios Baltatzis,

Rolandos Alexandros Potamias,

Evangelos Ververas,

Guanxiong Sun,

Jiankang Deng,

Stefanos Zafeiriou; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Baltatzis_2024_CVPR, author = {Baltatzis, Vasileios and Potamias, Rolandos Alexandros and Ververas, Evangelos and Sun, Guanxiong and Deng, Jiankang and Zafeiriou, Stefanos}, title = {Neural Sign Actors: A Diffusion Model for 3D Sign Language Production from Text}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1985-1995} }
On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm: Peng Sun,

Bei Shi,

Daiwei Yu,

Tao Lin; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sun_2024_CVPR, author = {Sun, Peng and Shi, Bei and Yu, Daiwei and Lin, Tao}, title = {On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9390-9399} }
Semantics-aware Motion Retargeting with Vision-Language Models: Haodong Zhang,

Zhike Chen,

Haocheng Xu,

Lei Hao,

Xiaofei Wu,

Songcen Xu,

Zhensong Zhang,

Yue Wang,

Rong Xiong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Zhang_2024_CVPR, author = {Zhang, Haodong and Chen, Zhike and Xu, Haocheng and Hao, Lei and Wu, Xiaofei and Xu, Songcen and Zhang, Zhensong and Wang, Yue and Xiong, Rong}, title = {Semantics-aware Motion Retargeting with Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {2155-2164} }
Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling: Leon Sick,

Dominik Engel,

Pedro Hermosilla,

Timo Ropinski; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Sick_2024_CVPR, author = {Sick, Leon and Engel, Dominik and Hermosilla, Pedro and Ropinski, Timo}, title = {Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3637-3646} }
RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models: Ozgur Kara,

Bariscan Kurtkaya,

Hidir Yesiltepe,

James M. Rehg,

Pinar Yanardag; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kara_2024_CVPR, author = {Kara, Ozgur and Kurtkaya, Bariscan and Yesiltepe, Hidir and Rehg, James M. and Yanardag, Pinar}, title = {RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6507-6516} }
Video-Based Human Pose Regression via Decoupled Space-Time Aggregation: Jijie He,

Wenwu Yang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{He_2024_CVPR, author = {He, Jijie and Yang, Wenwu}, title = {Video-Based Human Pose Regression via Decoupled Space-Time Aggregation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1022-1031} }
L-MAGIC: Language Model Assisted Generation of Images with Coherence: Zhipeng Cai,

Matthias Mueller,

Reiner Birkl,

Diana Wofk,

Shao-Yen Tseng,

Junda Cheng,

Gabriela Ben-Melech Stan,

Vasudev Lai,

Michael Paulitsch; [pdf] [supp]
[bibtex]
@InProceedings{Cai_2024_CVPR, author = {Cai, Zhipeng and Mueller, Matthias and Birkl, Reiner and Wofk, Diana and Tseng, Shao-Yen and Cheng, Junda and Stan, Gabriela Ben-Melech and Lai, Vasudev and Paulitsch, Michael}, title = {L-MAGIC: Language Model Assisted Generation of Images with Coherence}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {7049-7058} }
3D Face Tracking from 2D Video through Iterative Dense UV to Image Flow: Felix Taubner,

Prashant Raina,

Mathieu Tuli,

Eu Wern Teh,

Chul Lee,

Jinmiao Huang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Taubner_2024_CVPR, author = {Taubner, Felix and Raina, Prashant and Tuli, Mathieu and Teh, Eu Wern and Lee, Chul and Huang, Jinmiao}, title = {3D Face Tracking from 2D Video through Iterative Dense UV to Image Flow}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1227-1237} }
Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning: Desai Xie,

Jiahao Li,

Hao Tan,

Xin Sun,

Zhixin Shu,

Yi Zhou,

Sai Bi,

Sören Pirk,

Arie E. Kaufman; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xie_2024_CVPR, author = {Xie, Desai and Li, Jiahao and Tan, Hao and Sun, Xin and Shu, Zhixin and Zhou, Yi and Bi, Sai and Pirk, S\"oren and Kaufman, Arie E.}, title = {Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {6369-6379} }
Shadow Generation for Composite Image Using Diffusion Model: Qingyang Liu,

Junqi You,

Jianting Wang,

Xinhao Tao,

Bo Zhang,

Li Niu; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2024_CVPR, author = {Liu, Qingyang and You, Junqi and Wang, Jianting and Tao, Xinhao and Zhang, Bo and Niu, Li}, title = {Shadow Generation for Composite Image Using Diffusion Model}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8121-8130} }
DisCo: Disentangled Control for Realistic Human Dance Generation: Tan Wang,

Linjie Li,

Kevin Lin,

Yuanhao Zhai,

Chung-Ching Lin,

Zhengyuan Yang,

Hanwang Zhang,

Zicheng Liu,

Lijuan Wang; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Wang_2024_CVPR, author = {Wang, Tan and Li, Linjie and Lin, Kevin and Zhai, Yuanhao and Lin, Chung-Ching and Yang, Zhengyuan and Zhang, Hanwang and Liu, Zicheng and Wang, Lijuan}, title = {DisCo: Disentangled Control for Realistic Human Dance Generation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {9326-9336} }
GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces: Yingwenqi Jiang,

Jiadong Tu,

Yuan Liu,

Xifeng Gao,

Xiaoxiao Long,

Wenping Wang,

Yuexin Ma; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2024_CVPR, author = {Jiang, Yingwenqi and Tu, Jiadong and Liu, Yuan and Gao, Xifeng and Long, Xiaoxiao and Wang, Wenping and Ma, Yuexin}, title = {GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {5322-5332} }
pix2gestalt: Amodal Segmentation by Synthesizing Wholes: Ege Ozguroglu,

Ruoshi Liu,

Dídac Surís,

Dian Chen,

Achal Dave,

Pavel Tokmakov,

Carl Vondrick; [pdf]
[bibtex]
@InProceedings{Ozguroglu_2024_CVPR, author = {Ozguroglu, Ege and Liu, Ruoshi and Sur{\'\i}s, D{\'\i}dac and Chen, Dian and Dave, Achal and Tokmakov, Pavel and Vondrick, Carl}, title = {pix2gestalt: Amodal Segmentation by Synthesizing Wholes}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3931-3940} }
Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle: Hyeokjun Kweon,

Jihun Kim,

Kuk-Jin Yoon; [pdf] [supp]
[bibtex]
@InProceedings{Kweon_2024_CVPR, author = {Kweon, Hyeokjun and Kim, Jihun and Yoon, Kuk-Jin}, title = {Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {3721-3731} }
Forecasting of 3D Whole-body Human Poses with Grasping Objects: Haitao Yan,

Qiongjie Cui,

Jiexin Xie,

Shijie Guo; [pdf]
[bibtex]
@InProceedings{Yan_2024_CVPR, author = {Yan, Haitao and Cui, Qiongjie and Xie, Jiexin and Guo, Shijie}, title = {Forecasting of 3D Whole-body Human Poses with Grasping Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1726-1736} }
Accelerating Diffusion Sampling with Optimized Time Steps: Shuchen Xue,

Zhaoqiang Liu,

Fei Chen,

Shifeng Zhang,

Tianyang Hu,

Enze Xie,

Zhenguo Li; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Xue_2024_CVPR, author = {Xue, Shuchen and Liu, Zhaoqiang and Chen, Fei and Zhang, Shifeng and Hu, Tianyang and Xie, Enze and Li, Zhenguo}, title = {Accelerating Diffusion Sampling with Optimized Time Steps}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {8292-8301} }