Hierarchical Flow Diffusion for Efficient Frame Interpolation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916668495626240 |
|---|---|
| author | Hai, Yang Wang, Guo Su, Tan Jiang, Wenjie Hu, Yinlin |
| author_facet | Hai, Yang Wang, Guo Su, Tan Jiang, Wenjie Hu, Yinlin |
| contents | Most recent diffusion-based methods still show a large gap compared to non-diffusion methods for video frame interpolation, in both accuracy and efficiency. Most of them formulate the problem as a denoising procedure in latent space directly, which is less effective caused by the large latent space. We propose to model bilateral optical flow explicitly by hierarchical diffusion models, which has much smaller search space in the denoising procedure. Based on the flow diffusion model, we then use a flow-guided images synthesizer to produce the final result. We train the flow diffusion model and the image synthesizer end to end. Our method achieves state of the art in accuracy, and 10+ times faster than other diffusion-based methods. The project page is at: https://hfd-interpolation.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_00380 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hierarchical Flow Diffusion for Efficient Frame Interpolation Hai, Yang Wang, Guo Su, Tan Jiang, Wenjie Hu, Yinlin Computer Vision and Pattern Recognition Most recent diffusion-based methods still show a large gap compared to non-diffusion methods for video frame interpolation, in both accuracy and efficiency. Most of them formulate the problem as a denoising procedure in latent space directly, which is less effective caused by the large latent space. We propose to model bilateral optical flow explicitly by hierarchical diffusion models, which has much smaller search space in the denoising procedure. Based on the flow diffusion model, we then use a flow-guided images synthesizer to produce the final result. We train the flow diffusion model and the image synthesizer end to end. Our method achieves state of the art in accuracy, and 10+ times faster than other diffusion-based methods. The project page is at: https://hfd-interpolation.github.io. |
| title | Hierarchical Flow Diffusion for Efficient Frame Interpolation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.00380 |