AnimateScene: Camera-controllable Animation in Any Scene
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_ | 1866912928924434432 |
|---|---|
| author | Liu, Qingyang Gao, Bingjie Huang, Weiheng Zhang, Jun Sun, Zhongqian Wei, Yang Liu, Fengrui Peng, Zelin Ma, Qianli Yang, Shuai Liao, Zhaohe Zhao, Haonan Niu, Li |
| author_facet | Liu, Qingyang Gao, Bingjie Huang, Weiheng Zhang, Jun Sun, Zhongqian Wei, Yang Liu, Fengrui Peng, Zelin Ma, Qianli Yang, Shuai Liao, Zhaohe Zhao, Haonan Niu, Li |
| contents | Recent advances in 3D scene reconstruction and 4D human animation have broadened adoption, but integrating the two remains difficult. Key challenges include placing humans at plausible locations and scales without interpenetration, aligning lighting and style between humans and background, and handling dynamic camera trajectories. We introduce AnimateScene, a unified framework addressing these issues. First, an accurate placement module automatically determines realistic 3D positions and prevents collisions during motion. Second, we propose a training-free style alignment method that adapts the 4D human to match background illumination and appearance, achieving coherent composites. Finally, we design a joint post-reconstruction approach that incorporates camera trajectories for smooth, visually engaging motion videos. Experiments across diverse scenes and actions demonstrate that AnimateScene generates dynamic results with high geometric detail and strong spatiotemporal coherence. The project page is available at https://whynothaha.github.io/AnimateScene/AnimateScene.html. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_05982 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AnimateScene: Camera-controllable Animation in Any Scene Liu, Qingyang Gao, Bingjie Huang, Weiheng Zhang, Jun Sun, Zhongqian Wei, Yang Liu, Fengrui Peng, Zelin Ma, Qianli Yang, Shuai Liao, Zhaohe Zhao, Haonan Niu, Li Computer Vision and Pattern Recognition Recent advances in 3D scene reconstruction and 4D human animation have broadened adoption, but integrating the two remains difficult. Key challenges include placing humans at plausible locations and scales without interpenetration, aligning lighting and style between humans and background, and handling dynamic camera trajectories. We introduce AnimateScene, a unified framework addressing these issues. First, an accurate placement module automatically determines realistic 3D positions and prevents collisions during motion. Second, we propose a training-free style alignment method that adapts the 4D human to match background illumination and appearance, achieving coherent composites. Finally, we design a joint post-reconstruction approach that incorporates camera trajectories for smooth, visually engaging motion videos. Experiments across diverse scenes and actions demonstrate that AnimateScene generates dynamic results with high geometric detail and strong spatiotemporal coherence. The project page is available at https://whynothaha.github.io/AnimateScene/AnimateScene.html. |
| title | AnimateScene: Camera-controllable Animation in Any Scene |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.05982 |