4th edition of Computer Vision for Metaverse Workshop
Direction-Aware Hybrid Representation Learning for 3D Hand Pose and Shape Estimation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2025_CVPR, author = {Liu, Shiyong and Li, Zhihao and Tang, Xiao and Liu, Jianzhuang}, title = {Direction-Aware Hybrid Representation Learning for 3D Hand Pose and Shape Estimation}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {251-260} }
ePBR: Extended PBR Materials in Image Synthesis-
[pdf]
[arXiv]
[bibtex]@InProceedings{Guo_2025_CVPR, author = {Guo, Yu and Lao, Zhiqiang and Song, Xiyun and Zhou, Yubin and Lin, Zongfang and Yu, Heather}, title = {ePBR: Extended PBR Materials in Image Synthesis}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {327-336} }
SplatMesh: Interactive 3D Segmentation and Editing Using Mesh-Based Gaussian Splatting-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Zhou_2025_CVPR, author = {Zhou, Kaichen and Hong, Lanqing and Chang, Xinhai and Zhong, Yingji and Xie, Enze and Dong, Hao and Li, Zhihao and Yang, Yongxin and Li, Zhenguo and Zhang, Wei}, title = {SplatMesh: Interactive 3D Segmentation and Editing Using Mesh-Based Gaussian Splatting}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {305-316} }
ARC-NeRF: Area Ray Casting for Broader Unseen View Coverage in Few-shot Object Rendering-
[pdf]
[supp]
[bibtex]@InProceedings{Seo_2025_CVPR, author = {Seo, Seunghyeon and Chang, Yeonjin and Yoo, Jayeon and Lee, Seungwoo and Lee, Hojun and Kwak, Nojun}, title = {ARC-NeRF: Area Ray Casting for Broader Unseen View Coverage in Few-shot Object Rendering}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {273-283} }
PanoDreamer: Consistent Text to 360-Degree Scene Generation-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Xiong_2025_CVPR, author = {Xiong, Zhexiao and Chen, Zhang and Li, Zhong and Xu, Yi and Jacobs, Nathan}, title = {PanoDreamer: Consistent Text to 360-Degree Scene Generation}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {295-304} }
IL-NeRF: Incremental Learning for Neural Radiance Fields with Camera Pose Alignment-
[pdf]
[supp]
[bibtex]@InProceedings{Zhang_2025_CVPR, author = {Zhang, Letian and Li, Ming and Chen, Chen and Xu, Jie}, title = {IL-NeRF: Incremental Learning for Neural Radiance Fields with Camera Pose Alignment}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {358-368} }
FreBIS: Frequency-Based Stratification for Neural Implicit Surface Representations-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Sawada_2025_CVPR, author = {Sawada, Naoko and Miraldo, Pedro and Lohit, Suhas and Marks, Tim K. and Chatterjee, Moitreya}, title = {FreBIS: Frequency-Based Stratification for Neural Implicit Surface Representations}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {369-379} }
HumMorph: Generalized Dynamic Human Neural Fields from Few Views-
[pdf]
[supp]
[bibtex]@InProceedings{Zadrozny_2025_CVPR, author = {Zadro\.zny, Jakub and Bilen, Hakan}, title = {HumMorph: Generalized Dynamic Human Neural Fields from Few Views}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {348-357} }
PluckeRF: A Line-based 3D Representation for Few-view Reconstruction-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Bahrami_2025_CVPR, author = {Bahrami, Sam and Campbell, Dylan}, title = {PluckeRF: A Line-based 3D Representation for Few-view Reconstruction}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {317-326} }
DeclutterNeRF: Generative-Free 3D Scene Recovery for Occlusion Removal-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Liu_2025_CVPR, author = {Liu, Wanzhou and Xiong, Zhexiao and Li, Xinyu and Jacobs, Nathan}, title = {DeclutterNeRF: Generative-Free 3D Scene Recovery for Occlusion Removal}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {380-390} }
What Makes for a Good Stereoscopic Image?-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Tamir_2025_CVPR, author = {Tamir, Netanel and Amir, Shir and Itzhaky, Ranel and Atia, Noam and Sundaram, Shobhita and Fu, Stephanie and Sokolovsky, Ron and Isola, Phillip and Dekel, Tali and Zhang, Richard and Farber, Miriam}, title = {What Makes for a Good Stereoscopic Image?}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {261-272} }
OccludeNeRF: Geometry-aware 3D Scene Inpainting with Collaborative Score Distillation in NeRF-
[pdf]
[supp]
[bibtex]@InProceedings{Shi_2025_CVPR, author = {Shi, Jingyu and Luthra, Achleshwar and Li, Jiazhi and Gao, Xiang and Song, Xiyun and Lin, Zongfang and Gu, David and Yu, Heather}, title = {OccludeNeRF: Geometry-aware 3D Scene Inpainting with Collaborative Score Distillation in NeRF}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {284-294} }
FaceGest: A Comprehensive Facial Gesture Dataset for Human-Computer Interaction-
[pdf]
[bibtex]@InProceedings{--_2025_CVPR, author = {--, Yaseen and Jamil, Sonain}, title = {FaceGest: A Comprehensive Facial Gesture Dataset for Human-Computer Interaction}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {337-347} }