Diffusion-Based Low-Light Image Enhancement with Color and Luminance Priors
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908856994496512 |
|---|---|
| author | Fu, Xuanshuo Kang, Lei Vazquez-Corral, Javier |
| author_facet | Fu, Xuanshuo Kang, Lei Vazquez-Corral, Javier |
| contents | Low-light images often suffer from low contrast, noise, and color distortion, degrading visual quality and impairing downstream vision tasks. We propose a novel conditional diffusion framework for low-light image enhancement that incorporates a Structured Control Embedding Module (SCEM). SCEM decomposes a low-light image into four informative components including illumination, illumination-invariant features, shadow priors, and color-invariant cues. These components serve as control signals that condition a U-Net-based diffusion model trained with a simplified noise-prediction loss. Thus, the proposed SCEM equipped Diffusion method enforces structured enhancement guided by physical priors. In experiments, our model is trained only on the LOLv1 dataset and evaluated without fine-tuning on LOLv2-real, LSRW, DICM, MEF, and LIME. The method achieves state-of-the-art performance in quantitative and perceptual metrics, demonstrating strong generalization across benchmarks. https://casted.github.io/scem/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_00337 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Diffusion-Based Low-Light Image Enhancement with Color and Luminance Priors Fu, Xuanshuo Kang, Lei Vazquez-Corral, Javier Computer Vision and Pattern Recognition Low-light images often suffer from low contrast, noise, and color distortion, degrading visual quality and impairing downstream vision tasks. We propose a novel conditional diffusion framework for low-light image enhancement that incorporates a Structured Control Embedding Module (SCEM). SCEM decomposes a low-light image into four informative components including illumination, illumination-invariant features, shadow priors, and color-invariant cues. These components serve as control signals that condition a U-Net-based diffusion model trained with a simplified noise-prediction loss. Thus, the proposed SCEM equipped Diffusion method enforces structured enhancement guided by physical priors. In experiments, our model is trained only on the LOLv1 dataset and evaluated without fine-tuning on LOLv2-real, LSRW, DICM, MEF, and LIME. The method achieves state-of-the-art performance in quantitative and perceptual metrics, demonstrating strong generalization across benchmarks. https://casted.github.io/scem/. |
| title | Diffusion-Based Low-Light Image Enhancement with Color and Luminance Priors |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.00337 |