Motion-aware Latent Diffusion Models for Video Frame Interpolation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913455691268096 |
|---|---|
| author | Huang, Zhilin Yu, Yijie Yang, Ling Qin, Chujun Zheng, Bing Zheng, Xiawu Zhou, Zikun Wang, Yaowei Yang, Wenming |
| author_facet | Huang, Zhilin Yu, Yijie Yang, Ling Qin, Chujun Zheng, Bing Zheng, Xiawu Zhou, Zikun Wang, Yaowei Yang, Wenming |
| contents | With the advancement of AIGC, video frame interpolation (VFI) has become a crucial component in existing video generation frameworks, attracting widespread research interest. For the VFI task, the motion estimation between neighboring frames plays a crucial role in avoiding motion ambiguity. However, existing VFI methods always struggle to accurately predict the motion information between consecutive frames, and this imprecise estimation leads to blurred and visually incoherent interpolated frames. In this paper, we propose a novel diffusion framework, motion-aware latent diffusion models (MADiff), which is specifically designed for the VFI task. By incorporating motion priors between the conditional neighboring frames with the target interpolated frame predicted throughout the diffusion sampling procedure, MADiff progressively refines the intermediate outcomes, culminating in generating both visually smooth and realistic results. Extensive experiments conducted on benchmark datasets demonstrate that our method achieves state-of-the-art performance significantly outperforming existing approaches, especially under challenging scenarios involving dynamic textures with complex motion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_13534 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Motion-aware Latent Diffusion Models for Video Frame Interpolation Huang, Zhilin Yu, Yijie Yang, Ling Qin, Chujun Zheng, Bing Zheng, Xiawu Zhou, Zikun Wang, Yaowei Yang, Wenming Computer Vision and Pattern Recognition With the advancement of AIGC, video frame interpolation (VFI) has become a crucial component in existing video generation frameworks, attracting widespread research interest. For the VFI task, the motion estimation between neighboring frames plays a crucial role in avoiding motion ambiguity. However, existing VFI methods always struggle to accurately predict the motion information between consecutive frames, and this imprecise estimation leads to blurred and visually incoherent interpolated frames. In this paper, we propose a novel diffusion framework, motion-aware latent diffusion models (MADiff), which is specifically designed for the VFI task. By incorporating motion priors between the conditional neighboring frames with the target interpolated frame predicted throughout the diffusion sampling procedure, MADiff progressively refines the intermediate outcomes, culminating in generating both visually smooth and realistic results. Extensive experiments conducted on benchmark datasets demonstrate that our method achieves state-of-the-art performance significantly outperforming existing approaches, especially under challenging scenarios involving dynamic textures with complex motion. |
| title | Motion-aware Latent Diffusion Models for Video Frame Interpolation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.13534 |