Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2510.08561 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912642112684032 |
|---|---|
| author | Tanveer, Maham Zhou, Yang Niklaus, Simon Amiri, Ali Mahdavi Zhang, Hao Singh, Krishna Kumar Zhao, Nanxuan |
| author_facet | Tanveer, Maham Zhou, Yang Niklaus, Simon Amiri, Ali Mahdavi Zhang, Hao Singh, Krishna Kumar Zhao, Nanxuan |
| contents | Video inbetweening creates smooth and natural transitions between two image frames, making it an indispensable tool for video editing and long-form video synthesis. Existing works in this domain are unable to generate large, complex, or intricate motions. In particular, they cannot accommodate the versatility of user intents and generally lack fine control over the details of intermediate frames, leading to misalignment with the creative mind. To fill these gaps, we introduce MultiCOIN, a video inbetweening framework that allows multi-modal controls, including depth transition and layering, motion trajectories, text prompts, and target regions for movement localization, while achieving a balance between flexibility, ease of use, and precision for fine-grained video interpolation. To achieve this, we adopt the Diffusion Transformer (DiT) architecture as our video generative model, due to its proven capability to generate high-quality long videos. To ensure compatibility between DiT and our multi-modal controls, we map all motion controls into a common sparse and user-friendly point-based representation as the video/noise input. Further, to respect the variety of controls which operate at varying levels of granularity and influence, we separate content controls and motion controls into two branches to encode the required features before guiding the denoising process, resulting in two generators, one for motion and the other for content. Finally, we propose a stage-wise training strategy to ensure that our model learns the multi-modal controls smoothly. Extensive qualitative and quantitative experiments demonstrate that multi-modal controls enable a more dynamic, customizable, and contextually accurate visual narrative. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_08561 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MultiCOIN: Multi-Modal COntrollable Video INbetweening Tanveer, Maham Zhou, Yang Niklaus, Simon Amiri, Ali Mahdavi Zhang, Hao Singh, Krishna Kumar Zhao, Nanxuan Computer Vision and Pattern Recognition Video inbetweening creates smooth and natural transitions between two image frames, making it an indispensable tool for video editing and long-form video synthesis. Existing works in this domain are unable to generate large, complex, or intricate motions. In particular, they cannot accommodate the versatility of user intents and generally lack fine control over the details of intermediate frames, leading to misalignment with the creative mind. To fill these gaps, we introduce MultiCOIN, a video inbetweening framework that allows multi-modal controls, including depth transition and layering, motion trajectories, text prompts, and target regions for movement localization, while achieving a balance between flexibility, ease of use, and precision for fine-grained video interpolation. To achieve this, we adopt the Diffusion Transformer (DiT) architecture as our video generative model, due to its proven capability to generate high-quality long videos. To ensure compatibility between DiT and our multi-modal controls, we map all motion controls into a common sparse and user-friendly point-based representation as the video/noise input. Further, to respect the variety of controls which operate at varying levels of granularity and influence, we separate content controls and motion controls into two branches to encode the required features before guiding the denoising process, resulting in two generators, one for motion and the other for content. Finally, we propose a stage-wise training strategy to ensure that our model learns the multi-modal controls smoothly. Extensive qualitative and quantitative experiments demonstrate that multi-modal controls enable a more dynamic, customizable, and contextually accurate visual narrative. |
| title | MultiCOIN: Multi-Modal COntrollable Video INbetweening |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.08561 |