Diffusion Restoration Adapter for Real-World Image 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_ | 1866910850151874560 |
|---|---|
| author | Liang, Hanbang Wang, Zhen Deng, Weihui |
| author_facet | Liang, Hanbang Wang, Zhen Deng, Weihui |
| contents | Diffusion models have demonstrated their powerful image generation capabilities, effectively fitting highly complex image distributions. These models can serve as strong priors for image restoration. Existing methods often utilize techniques like ControlNet to sample high quality images with low quality images from these priors. However, ControlNet typically involves copying a large part of the original network, resulting in a significantly large number of parameters as the prior scales up. In this paper, we propose a relatively lightweight Adapter that leverages the powerful generative capabilities of pretrained priors to achieve photo-realistic image restoration. The Adapters can be adapt to both denoising UNet and DiT, and performs excellent. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_20679 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Diffusion Restoration Adapter for Real-World Image Restoration Liang, Hanbang Wang, Zhen Deng, Weihui Computer Vision and Pattern Recognition Diffusion models have demonstrated their powerful image generation capabilities, effectively fitting highly complex image distributions. These models can serve as strong priors for image restoration. Existing methods often utilize techniques like ControlNet to sample high quality images with low quality images from these priors. However, ControlNet typically involves copying a large part of the original network, resulting in a significantly large number of parameters as the prior scales up. In this paper, we propose a relatively lightweight Adapter that leverages the powerful generative capabilities of pretrained priors to achieve photo-realistic image restoration. The Adapters can be adapt to both denoising UNet and DiT, and performs excellent. |
| title | Diffusion Restoration Adapter for Real-World Image Restoration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.20679 |