DAM-VSR: Disentanglement of Appearance and Motion for Video Super-Resolution
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913921543176192 |
|---|---|
| author | Kong, Zhe Li, Le Zhang, Yong Gao, Feng Yang, Shaoshu Wang, Tao Zhang, Kaihao Kang, Zhuoliang Wei, Xiaoming Chen, Guanying Luo, Wenhan |
| author_facet | Kong, Zhe Li, Le Zhang, Yong Gao, Feng Yang, Shaoshu Wang, Tao Zhang, Kaihao Kang, Zhuoliang Wei, Xiaoming Chen, Guanying Luo, Wenhan |
| contents | Real-world video super-resolution (VSR) presents significant challenges due to complex and unpredictable degradations. Although some recent methods utilize image diffusion models for VSR and have shown improved detail generation capabilities, they still struggle to produce temporally consistent frames. We attempt to use Stable Video Diffusion (SVD) combined with ControlNet to address this issue. However, due to the intrinsic image-animation characteristics of SVD, it is challenging to generate fine details using only low-quality videos. To tackle this problem, we propose DAM-VSR, an appearance and motion disentanglement framework for VSR. This framework disentangles VSR into appearance enhancement and motion control problems. Specifically, appearance enhancement is achieved through reference image super-resolution, while motion control is achieved through video ControlNet. This disentanglement fully leverages the generative prior of video diffusion models and the detail generation capabilities of image super-resolution models. Furthermore, equipped with the proposed motion-aligned bidirectional sampling strategy, DAM-VSR can conduct VSR on longer input videos. DAM-VSR achieves state-of-the-art performance on real-world data and AIGC data, demonstrating its powerful detail generation capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_01012 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DAM-VSR: Disentanglement of Appearance and Motion for Video Super-Resolution Kong, Zhe Li, Le Zhang, Yong Gao, Feng Yang, Shaoshu Wang, Tao Zhang, Kaihao Kang, Zhuoliang Wei, Xiaoming Chen, Guanying Luo, Wenhan Computer Vision and Pattern Recognition Real-world video super-resolution (VSR) presents significant challenges due to complex and unpredictable degradations. Although some recent methods utilize image diffusion models for VSR and have shown improved detail generation capabilities, they still struggle to produce temporally consistent frames. We attempt to use Stable Video Diffusion (SVD) combined with ControlNet to address this issue. However, due to the intrinsic image-animation characteristics of SVD, it is challenging to generate fine details using only low-quality videos. To tackle this problem, we propose DAM-VSR, an appearance and motion disentanglement framework for VSR. This framework disentangles VSR into appearance enhancement and motion control problems. Specifically, appearance enhancement is achieved through reference image super-resolution, while motion control is achieved through video ControlNet. This disentanglement fully leverages the generative prior of video diffusion models and the detail generation capabilities of image super-resolution models. Furthermore, equipped with the proposed motion-aligned bidirectional sampling strategy, DAM-VSR can conduct VSR on longer input videos. DAM-VSR achieves state-of-the-art performance on real-world data and AIGC data, demonstrating its powerful detail generation capabilities. |
| title | DAM-VSR: Disentanglement of Appearance and Motion for Video Super-Resolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.01012 |