Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929269453619200 |
|---|---|
| author | He, Chunming Fang, Chengyu Zhang, Yulun Ye, Tian Li, Kai Tang, Longxiang Guo, Zhenhua Li, Xiu Farsiu, Sina |
| author_facet | He, Chunming Fang, Chengyu Zhang, Yulun Ye, Tian Li, Kai Tang, Longxiang Guo, Zhenhua Li, Xiu Farsiu, Sina |
| contents | Illumination degradation image restoration (IDIR) techniques aim to improve the visibility of degraded images and mitigate the adverse effects of deteriorated illumination. Among these algorithms, diffusion model (DM)-based methods have shown promising performance but are often burdened by heavy computational demands and pixel misalignment issues when predicting the image-level distribution. To tackle these problems, we propose to leverage DM within a compact latent space to generate concise guidance priors and introduce a novel solution called Reti-Diff for the IDIR task. Reti-Diff comprises two key components: the Retinex-based latent DM (RLDM) and the Retinex-guided transformer (RGformer). To ensure detailed reconstruction and illumination correction, RLDM is empowered to acquire Retinex knowledge and extract reflectance and illumination priors. These priors are subsequently utilized by RGformer to guide the decomposition of image features into their respective reflectance and illumination components. Following this, RGformer further enhances and consolidates the decomposed features, resulting in the production of refined images with consistent content and robustness to handle complex degradation scenarios. Extensive experiments show that Reti-Diff outperforms existing methods on three IDIR tasks, as well as downstream applications. Code will be available at \url{https://github.com/ChunmingHe/Reti-Diff}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_11638 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model He, Chunming Fang, Chengyu Zhang, Yulun Ye, Tian Li, Kai Tang, Longxiang Guo, Zhenhua Li, Xiu Farsiu, Sina Computer Vision and Pattern Recognition Illumination degradation image restoration (IDIR) techniques aim to improve the visibility of degraded images and mitigate the adverse effects of deteriorated illumination. Among these algorithms, diffusion model (DM)-based methods have shown promising performance but are often burdened by heavy computational demands and pixel misalignment issues when predicting the image-level distribution. To tackle these problems, we propose to leverage DM within a compact latent space to generate concise guidance priors and introduce a novel solution called Reti-Diff for the IDIR task. Reti-Diff comprises two key components: the Retinex-based latent DM (RLDM) and the Retinex-guided transformer (RGformer). To ensure detailed reconstruction and illumination correction, RLDM is empowered to acquire Retinex knowledge and extract reflectance and illumination priors. These priors are subsequently utilized by RGformer to guide the decomposition of image features into their respective reflectance and illumination components. Following this, RGformer further enhances and consolidates the decomposed features, resulting in the production of refined images with consistent content and robustness to handle complex degradation scenarios. Extensive experiments show that Reti-Diff outperforms existing methods on three IDIR tasks, as well as downstream applications. Code will be available at \url{https://github.com/ChunmingHe/Reti-Diff}. |
| title | Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2311.11638 |