R3-Avatar: Record and Retrieve Temporal Codebook for Reconstructing Photorealistic Human Avatars
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916653902594048 |
|---|---|
| author | Zhan, Yifan Xu, Wangze Zhu, Qingtian Niu, Muyao Ma, Mingze Liu, Yifei Zhong, Zhihang Sun, Xiao Zheng, Yinqiang |
| author_facet | Zhan, Yifan Xu, Wangze Zhu, Qingtian Niu, Muyao Ma, Mingze Liu, Yifei Zhong, Zhihang Sun, Xiao Zheng, Yinqiang |
| contents | We present R3-Avatar, incorporating a temporal codebook, to overcome the inability of human avatars to be both animatable and of high-fidelity rendering quality. Existing video-based reconstruction of 3D human avatars either focuses solely on rendering, lacking animation support, or learns a pose-appearance mapping for animating, which degrades under limited training poses or complex clothing. In this paper, we adopt a "record-retrieve-reconstruct" strategy that ensures high-quality rendering from novel views while mitigating degradation in novel poses. Specifically, disambiguating timestamps record temporal appearance variations in a codebook, ensuring high-fidelity novel-view rendering, while novel poses retrieve corresponding timestamps by matching the most similar training poses for augmented appearance. Our R3-Avatar outperforms cutting-edge video-based human avatar reconstruction, particularly in overcoming visual quality degradation in extreme scenarios with limited training human poses and complex clothing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_12751 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | R3-Avatar: Record and Retrieve Temporal Codebook for Reconstructing Photorealistic Human Avatars Zhan, Yifan Xu, Wangze Zhu, Qingtian Niu, Muyao Ma, Mingze Liu, Yifei Zhong, Zhihang Sun, Xiao Zheng, Yinqiang Computer Vision and Pattern Recognition We present R3-Avatar, incorporating a temporal codebook, to overcome the inability of human avatars to be both animatable and of high-fidelity rendering quality. Existing video-based reconstruction of 3D human avatars either focuses solely on rendering, lacking animation support, or learns a pose-appearance mapping for animating, which degrades under limited training poses or complex clothing. In this paper, we adopt a "record-retrieve-reconstruct" strategy that ensures high-quality rendering from novel views while mitigating degradation in novel poses. Specifically, disambiguating timestamps record temporal appearance variations in a codebook, ensuring high-fidelity novel-view rendering, while novel poses retrieve corresponding timestamps by matching the most similar training poses for augmented appearance. Our R3-Avatar outperforms cutting-edge video-based human avatar reconstruction, particularly in overcoming visual quality degradation in extreme scenarios with limited training human poses and complex clothing. |
| title | R3-Avatar: Record and Retrieve Temporal Codebook for Reconstructing Photorealistic Human Avatars |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.12751 |