FastAnimate: Towards Learnable Template Construction and Pose Deformation for Fast 3D Human Avatar Animation
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_ | 1866914176011599872 |
|---|---|
| author | Shu, Jian Yao, Nanjie Zhang, Gangjian Ren, Junlong Feng, Yu Wang, Hao |
| author_facet | Shu, Jian Yao, Nanjie Zhang, Gangjian Ren, Junlong Feng, Yu Wang, Hao |
| contents | 3D human avatar animation aims at transforming a human avatar from an arbitrary initial pose to a specified target pose using deformation algorithms. Existing approaches typically divide this task into two stages: canonical template construction and target pose deformation. However, current template construction methods demand extensive skeletal rigging and often produce artifacts for specific poses. Moreover, target pose deformation suffers from structural distortions caused by Linear Blend Skinning (LBS), which significantly undermines animation realism. To address these problems, we propose a unified learning-based framework to address both challenges in two phases. For the former phase, to overcome the inefficiencies and artifacts during template construction, we leverage a U-Net architecture that decouples texture and pose information in a feed-forward process, enabling fast generation of a human template. For the latter phase, we propose a data-driven refinement technique that enhances structural integrity. Extensive experiments show that our model delivers consistent performance across diverse poses with an optimal balance between efficiency and quality,surpassing state-of-the-art (SOTA) methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_01444 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FastAnimate: Towards Learnable Template Construction and Pose Deformation for Fast 3D Human Avatar Animation Shu, Jian Yao, Nanjie Zhang, Gangjian Ren, Junlong Feng, Yu Wang, Hao Computer Vision and Pattern Recognition 3D human avatar animation aims at transforming a human avatar from an arbitrary initial pose to a specified target pose using deformation algorithms. Existing approaches typically divide this task into two stages: canonical template construction and target pose deformation. However, current template construction methods demand extensive skeletal rigging and often produce artifacts for specific poses. Moreover, target pose deformation suffers from structural distortions caused by Linear Blend Skinning (LBS), which significantly undermines animation realism. To address these problems, we propose a unified learning-based framework to address both challenges in two phases. For the former phase, to overcome the inefficiencies and artifacts during template construction, we leverage a U-Net architecture that decouples texture and pose information in a feed-forward process, enabling fast generation of a human template. For the latter phase, we propose a data-driven refinement technique that enhances structural integrity. Extensive experiments show that our model delivers consistent performance across diverse poses with an optimal balance between efficiency and quality,surpassing state-of-the-art (SOTA) methods. |
| title | FastAnimate: Towards Learnable Template Construction and Pose Deformation for Fast 3D Human Avatar Animation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.01444 |