CoMo: Compositional Motion Customization for Text-to-Video Generation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912671937331200 |
|---|---|
| author | Xu, Youcan Wang, Zhen Shi, Jiaxin Li, Kexin Shao, Feifei Xiao, Jun Yang, Yi Yu, Jun Chen, Long |
| author_facet | Xu, Youcan Wang, Zhen Shi, Jiaxin Li, Kexin Shao, Feifei Xiao, Jun Yang, Yi Yu, Jun Chen, Long |
| contents | While recent text-to-video models excel at generating diverse scenes, they struggle with precise motion control, particularly for complex, multi-subject motions. Although methods for single-motion customization have been developed to address this gap, they fail in compositional scenarios due to two primary challenges: motion-appearance entanglement and ineffective multi-motion blending. This paper introduces CoMo, a novel framework for $\textbf{compositional motion customization}$ in text-to-video generation, enabling the synthesis of multiple, distinct motions within a single video. CoMo addresses these issues through a two-phase approach. First, in the single-motion learning phase, a static-dynamic decoupled tuning paradigm disentangles motion from appearance to learn a motion-specific module. Second, in the multi-motion composition phase, a plug-and-play divide-and-merge strategy composes these learned motions without additional training by spatially isolating their influence during the denoising process. To facilitate research in this new domain, we also introduce a new benchmark and a novel evaluation metric designed to assess multi-motion fidelity and blending. Extensive experiments demonstrate that CoMo achieves state-of-the-art performance, significantly advancing the capabilities of controllable video generation. Our project page is at https://como6.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_23007 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CoMo: Compositional Motion Customization for Text-to-Video Generation Xu, Youcan Wang, Zhen Shi, Jiaxin Li, Kexin Shao, Feifei Xiao, Jun Yang, Yi Yu, Jun Chen, Long Computer Vision and Pattern Recognition While recent text-to-video models excel at generating diverse scenes, they struggle with precise motion control, particularly for complex, multi-subject motions. Although methods for single-motion customization have been developed to address this gap, they fail in compositional scenarios due to two primary challenges: motion-appearance entanglement and ineffective multi-motion blending. This paper introduces CoMo, a novel framework for $\textbf{compositional motion customization}$ in text-to-video generation, enabling the synthesis of multiple, distinct motions within a single video. CoMo addresses these issues through a two-phase approach. First, in the single-motion learning phase, a static-dynamic decoupled tuning paradigm disentangles motion from appearance to learn a motion-specific module. Second, in the multi-motion composition phase, a plug-and-play divide-and-merge strategy composes these learned motions without additional training by spatially isolating their influence during the denoising process. To facilitate research in this new domain, we also introduce a new benchmark and a novel evaluation metric designed to assess multi-motion fidelity and blending. Extensive experiments demonstrate that CoMo achieves state-of-the-art performance, significantly advancing the capabilities of controllable video generation. Our project page is at https://como6.github.io/. |
| title | CoMo: Compositional Motion Customization for Text-to-Video Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.23007 |