PersonaAnimator: Personalized Motion Transfer from Unconstrained Videos
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_ | 1866914143237308416 |
|---|---|
| author | Qian, Ziyun Xiao, Runyu Tu, Shuyuan Xue, Wei Yang, Dingkang Li, Mingcheng Kou, Dongliang Han, Minghao Chen, Zizhi Zhang, Lihua |
| author_facet | Qian, Ziyun Xiao, Runyu Tu, Shuyuan Xue, Wei Yang, Dingkang Li, Mingcheng Kou, Dongliang Han, Minghao Chen, Zizhi Zhang, Lihua |
| contents | Recent advances in motion generation show remarkable progress. However, several limitations remain: (1) Existing pose-guided character motion transfer methods merely replicate motion without learning its style characteristics, resulting in inexpressive characters. (2) Motion style transfer methods rely heavily on motion capture data, which is difficult to obtain. (3) Generated motions sometimes violate physical laws. To address these challenges, this paper pioneers a new task: Video-to-Video Motion Personalization. We propose a novel framework, PersonaAnimator, which learns personalized motion patterns directly from unconstrained videos. This enables personalized motion transfer. To support this task, we introduce PersonaVid, the first video-based personalized motion dataset. It contains 20 motion content categories and 120 motion style categories. We further propose a Physics-aware Motion Style Regularization mechanism to enforce physical plausibility in the generated motions. Extensive experiments show that PersonaAnimator outperforms state-of-the-art motion transfer methods and sets a new benchmark for the Video-to-Video Motion Personalization task. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_19895 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PersonaAnimator: Personalized Motion Transfer from Unconstrained Videos Qian, Ziyun Xiao, Runyu Tu, Shuyuan Xue, Wei Yang, Dingkang Li, Mingcheng Kou, Dongliang Han, Minghao Chen, Zizhi Zhang, Lihua Computer Vision and Pattern Recognition Recent advances in motion generation show remarkable progress. However, several limitations remain: (1) Existing pose-guided character motion transfer methods merely replicate motion without learning its style characteristics, resulting in inexpressive characters. (2) Motion style transfer methods rely heavily on motion capture data, which is difficult to obtain. (3) Generated motions sometimes violate physical laws. To address these challenges, this paper pioneers a new task: Video-to-Video Motion Personalization. We propose a novel framework, PersonaAnimator, which learns personalized motion patterns directly from unconstrained videos. This enables personalized motion transfer. To support this task, we introduce PersonaVid, the first video-based personalized motion dataset. It contains 20 motion content categories and 120 motion style categories. We further propose a Physics-aware Motion Style Regularization mechanism to enforce physical plausibility in the generated motions. Extensive experiments show that PersonaAnimator outperforms state-of-the-art motion transfer methods and sets a new benchmark for the Video-to-Video Motion Personalization task. |
| title | PersonaAnimator: Personalized Motion Transfer from Unconstrained Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.19895 |