Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolution
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910175140511744 |
|---|---|
| author | Guo, Jinpei Ji, Yifei Wang, Shengwei Chen, Zheng Wang, Yufei Ma, Sizhuo Guo, Yong Li, Baiang Zhang, Jusheng Zhang, Yulun Wang, Jian |
| author_facet | Guo, Jinpei Ji, Yifei Wang, Shengwei Chen, Zheng Wang, Yufei Ma, Sizhuo Guo, Yong Li, Baiang Zhang, Jusheng Zhang, Yulun Wang, Jian |
| contents | Diffusion models have recently shown promising results for video super-resolution (VSR). However, directly adapting generative diffusion models to VSR can result in redundancy, since low-quality videos already preserve substantial content information. Such redundancy leads to increased computational overhead and learning burden, as the model performs superfluous operations and must learn to filter out irrelevant information. To address this problem, we propose OASIS, an efficient $\textbf{o}$ne-step diffusion model with $\textbf{a}$ttention $\textbf{s}$pecialization for real-world v$\textbf{i}$deo $\textbf{s}$uper-resolution. OASIS incorporates an attention specialization routing that assigns attention heads to different patterns according to their intrinsic behaviors. This routing mitigates redundancy while effectively preserving pretrained knowledge, allowing diffusion models to better adapt to VSR and achieve stronger performance. Moreover, we propose a simple yet effective progressive training strategy, which starts with temporally consistent degradations and then shifts to inconsistent settings. This strategy facilitates learning under complex degradations. Extensive experiments demonstrate that OASIS achieves state-of-the-art performance on both synthetic and real-world datasets. OASIS also provides superior inference speed, offering a $\textbf{6.2$\times$}$ speedup over one-step diffusion baselines such as SeedVR2. The code will be available at \href{https://github.com/jp-guo/OASIS}{https://github.com/jp-guo/OASIS}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23980 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolution Guo, Jinpei Ji, Yifei Wang, Shengwei Chen, Zheng Wang, Yufei Ma, Sizhuo Guo, Yong Li, Baiang Zhang, Jusheng Zhang, Yulun Wang, Jian Computer Vision and Pattern Recognition Diffusion models have recently shown promising results for video super-resolution (VSR). However, directly adapting generative diffusion models to VSR can result in redundancy, since low-quality videos already preserve substantial content information. Such redundancy leads to increased computational overhead and learning burden, as the model performs superfluous operations and must learn to filter out irrelevant information. To address this problem, we propose OASIS, an efficient $\textbf{o}$ne-step diffusion model with $\textbf{a}$ttention $\textbf{s}$pecialization for real-world v$\textbf{i}$deo $\textbf{s}$uper-resolution. OASIS incorporates an attention specialization routing that assigns attention heads to different patterns according to their intrinsic behaviors. This routing mitigates redundancy while effectively preserving pretrained knowledge, allowing diffusion models to better adapt to VSR and achieve stronger performance. Moreover, we propose a simple yet effective progressive training strategy, which starts with temporally consistent degradations and then shifts to inconsistent settings. This strategy facilitates learning under complex degradations. Extensive experiments demonstrate that OASIS achieves state-of-the-art performance on both synthetic and real-world datasets. OASIS also provides superior inference speed, offering a $\textbf{6.2$\times$}$ speedup over one-step diffusion baselines such as SeedVR2. The code will be available at \href{https://github.com/jp-guo/OASIS}{https://github.com/jp-guo/OASIS}. |
| title | Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.23980 |