Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control
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_ | 1866929667456368640 |
|---|---|
| author | Gu, Zekai Yan, Rui Lu, Jiahao Li, Peng Dou, Zhiyang Si, Chenyang Dong, Zhen Liu, Qifeng Lin, Cheng Liu, Ziwei Wang, Wenping Liu, Yuan |
| author_facet | Gu, Zekai Yan, Rui Lu, Jiahao Li, Peng Dou, Zhiyang Si, Chenyang Dong, Zhen Liu, Qifeng Lin, Cheng Liu, Ziwei Wang, Wenping Liu, Yuan |
| contents | Diffusion models have demonstrated impressive performance in generating high-quality videos from text prompts or images. However, precise control over the video generation process, such as camera manipulation or content editing, remains a significant challenge. Existing methods for controlled video generation are typically limited to a single control type, lacking the flexibility to handle diverse control demands. In this paper, we introduce Diffusion as Shader (DaS), a novel approach that supports multiple video control tasks within a unified architecture. Our key insight is that achieving versatile video control necessitates leveraging 3D control signals, as videos are fundamentally 2D renderings of dynamic 3D content. Unlike prior methods limited to 2D control signals, DaS leverages 3D tracking videos as control inputs, making the video diffusion process inherently 3D-aware. This innovation allows DaS to achieve a wide range of video controls by simply manipulating the 3D tracking videos. A further advantage of using 3D tracking videos is their ability to effectively link frames, significantly enhancing the temporal consistency of the generated videos. With just 3 days of fine-tuning on 8 H800 GPUs using less than 10k videos, DaS demonstrates strong control capabilities across diverse tasks, including mesh-to-video generation, camera control, motion transfer, and object manipulation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_03847 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control Gu, Zekai Yan, Rui Lu, Jiahao Li, Peng Dou, Zhiyang Si, Chenyang Dong, Zhen Liu, Qifeng Lin, Cheng Liu, Ziwei Wang, Wenping Liu, Yuan Computer Vision and Pattern Recognition Artificial Intelligence Graphics Diffusion models have demonstrated impressive performance in generating high-quality videos from text prompts or images. However, precise control over the video generation process, such as camera manipulation or content editing, remains a significant challenge. Existing methods for controlled video generation are typically limited to a single control type, lacking the flexibility to handle diverse control demands. In this paper, we introduce Diffusion as Shader (DaS), a novel approach that supports multiple video control tasks within a unified architecture. Our key insight is that achieving versatile video control necessitates leveraging 3D control signals, as videos are fundamentally 2D renderings of dynamic 3D content. Unlike prior methods limited to 2D control signals, DaS leverages 3D tracking videos as control inputs, making the video diffusion process inherently 3D-aware. This innovation allows DaS to achieve a wide range of video controls by simply manipulating the 3D tracking videos. A further advantage of using 3D tracking videos is their ability to effectively link frames, significantly enhancing the temporal consistency of the generated videos. With just 3 days of fine-tuning on 8 H800 GPUs using less than 10k videos, DaS demonstrates strong control capabilities across diverse tasks, including mesh-to-video generation, camera control, motion transfer, and object manipulation. |
| title | Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics |
| url | https://arxiv.org/abs/2501.03847 |