FlexAM: Flexible Appearance-Motion Decomposition for Versatile Video Generation Control
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915797077590016 |
|---|---|
| author | Sheng, Mingzhi Gu, Zekai Li, Peng Lin, Cheng Guo, Hao-Xiang Chen, Ying-Cong Liu, Yuan |
| author_facet | Sheng, Mingzhi Gu, Zekai Li, Peng Lin, Cheng Guo, Hao-Xiang Chen, Ying-Cong Liu, Yuan |
| contents | Effective and generalizable control in video generation remains a significant challenge. While many methods rely on ambiguous or task-specific signals, we argue that a fundamental disentanglement of "appearance" and "motion" provides a more robust and scalable pathway. We propose FlexAM, a unified framework built upon a novel 3D control signal. This signal represents video dynamics as a point cloud, introducing three key enhancements: multi-frequency positional encoding to distinguish fine-grained motion, depth-aware positional encoding, and a flexible control signal for balancing precision and generative quality. This representation allows FlexAM to effectively disentangle appearance and motion, enabling a wide range of tasks including I2V/V2V editing, camera control, and spatial object editing. Extensive experiments demonstrate that FlexAM achieves superior performance across all evaluated tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13185 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FlexAM: Flexible Appearance-Motion Decomposition for Versatile Video Generation Control Sheng, Mingzhi Gu, Zekai Li, Peng Lin, Cheng Guo, Hao-Xiang Chen, Ying-Cong Liu, Yuan Computer Vision and Pattern Recognition Graphics Effective and generalizable control in video generation remains a significant challenge. While many methods rely on ambiguous or task-specific signals, we argue that a fundamental disentanglement of "appearance" and "motion" provides a more robust and scalable pathway. We propose FlexAM, a unified framework built upon a novel 3D control signal. This signal represents video dynamics as a point cloud, introducing three key enhancements: multi-frequency positional encoding to distinguish fine-grained motion, depth-aware positional encoding, and a flexible control signal for balancing precision and generative quality. This representation allows FlexAM to effectively disentangle appearance and motion, enabling a wide range of tasks including I2V/V2V editing, camera control, and spatial object editing. Extensive experiments demonstrate that FlexAM achieves superior performance across all evaluated tasks. |
| title | FlexAM: Flexible Appearance-Motion Decomposition for Versatile Video Generation Control |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2602.13185 |