AnimateAnywhere: Rouse the Background in Human Image Animation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909750485057536 |
|---|---|
| author | Liu, Xiaoyu Yao, Mingshuai Zhang, Yabo Lin, Xianhui Ren, Peiran Li, Xiaoming Liu, Ming Zuo, Wangmeng |
| author_facet | Liu, Xiaoyu Yao, Mingshuai Zhang, Yabo Lin, Xianhui Ren, Peiran Li, Xiaoming Liu, Ming Zuo, Wangmeng |
| contents | Human image animation aims to generate human videos of given characters and backgrounds that adhere to the desired pose sequence. However, existing methods focus more on human actions while neglecting the generation of background, which typically leads to static results or inharmonious movements. The community has explored camera pose-guided animation tasks, yet preparing the camera trajectory is impractical for most entertainment applications and ordinary users. As a remedy, we present an AnimateAnywhere framework, rousing the background in human image animation without requirements on camera trajectories. In particular, based on our key insight that the movement of the human body often reflects the motion of the background, we introduce a background motion learner (BML) to learn background motions from human pose sequences. To encourage the model to learn more accurate cross-frame correspondences, we further deploy an epipolar constraint on the 3D attention map. Specifically, the mask used to suppress geometrically unreasonable attention is carefully constructed by combining an epipolar mask and the current 3D attention map. Extensive experiments demonstrate that our AnimateAnywhere effectively learns the background motion from human pose sequences, achieving state-of-the-art performance in generating human animation results with vivid and realistic backgrounds. The source code and model will be available at https://github.com/liuxiaoyu1104/AnimateAnywhere. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_19834 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AnimateAnywhere: Rouse the Background in Human Image Animation Liu, Xiaoyu Yao, Mingshuai Zhang, Yabo Lin, Xianhui Ren, Peiran Li, Xiaoming Liu, Ming Zuo, Wangmeng Computer Vision and Pattern Recognition Human image animation aims to generate human videos of given characters and backgrounds that adhere to the desired pose sequence. However, existing methods focus more on human actions while neglecting the generation of background, which typically leads to static results or inharmonious movements. The community has explored camera pose-guided animation tasks, yet preparing the camera trajectory is impractical for most entertainment applications and ordinary users. As a remedy, we present an AnimateAnywhere framework, rousing the background in human image animation without requirements on camera trajectories. In particular, based on our key insight that the movement of the human body often reflects the motion of the background, we introduce a background motion learner (BML) to learn background motions from human pose sequences. To encourage the model to learn more accurate cross-frame correspondences, we further deploy an epipolar constraint on the 3D attention map. Specifically, the mask used to suppress geometrically unreasonable attention is carefully constructed by combining an epipolar mask and the current 3D attention map. Extensive experiments demonstrate that our AnimateAnywhere effectively learns the background motion from human pose sequences, achieving state-of-the-art performance in generating human animation results with vivid and realistic backgrounds. The source code and model will be available at https://github.com/liuxiaoyu1104/AnimateAnywhere. |
| title | AnimateAnywhere: Rouse the Background in Human Image Animation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.19834 |