SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration
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_ | 1866915208858959872 |
|---|---|
| author | Wang, Jianyi Lin, Zhijie Wei, Meng Zhao, Yang Yang, Ceyuan Xiao, Fei Loy, Chen Change Jiang, Lu |
| author_facet | Wang, Jianyi Lin, Zhijie Wei, Meng Zhao, Yang Yang, Ceyuan Xiao, Fei Loy, Chen Change Jiang, Lu |
| contents | Video restoration poses non-trivial challenges in maintaining fidelity while recovering temporally consistent details from unknown degradations in the wild. Despite recent advances in diffusion-based restoration, these methods often face limitations in generation capability and sampling efficiency. In this work, we present SeedVR, a diffusion transformer designed to handle real-world video restoration with arbitrary length and resolution. The core design of SeedVR lies in the shifted window attention that facilitates effective restoration on long video sequences. SeedVR further supports variable-sized windows near the boundary of both spatial and temporal dimensions, overcoming the resolution constraints of traditional window attention. Equipped with contemporary practices, including causal video autoencoder, mixed image and video training, and progressive training, SeedVR achieves highly-competitive performance on both synthetic and real-world benchmarks, as well as AI-generated videos. Extensive experiments demonstrate SeedVR's superiority over existing methods for generic video restoration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01320 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration Wang, Jianyi Lin, Zhijie Wei, Meng Zhao, Yang Yang, Ceyuan Xiao, Fei Loy, Chen Change Jiang, Lu Computer Vision and Pattern Recognition Video restoration poses non-trivial challenges in maintaining fidelity while recovering temporally consistent details from unknown degradations in the wild. Despite recent advances in diffusion-based restoration, these methods often face limitations in generation capability and sampling efficiency. In this work, we present SeedVR, a diffusion transformer designed to handle real-world video restoration with arbitrary length and resolution. The core design of SeedVR lies in the shifted window attention that facilitates effective restoration on long video sequences. SeedVR further supports variable-sized windows near the boundary of both spatial and temporal dimensions, overcoming the resolution constraints of traditional window attention. Equipped with contemporary practices, including causal video autoencoder, mixed image and video training, and progressive training, SeedVR achieves highly-competitive performance on both synthetic and real-world benchmarks, as well as AI-generated videos. Extensive experiments demonstrate SeedVR's superiority over existing methods for generic video restoration. |
| title | SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.01320 |