Research map / Image generation / Image restoration
LUCE: Constrained Curve-Domain Guidance for Training-Free Low-Light Enhancement with Hue-Preserving Decoupling
Yijie Wei, Weiran Li, Yeqiang Liu, Mina Han, Xue Liu, Zhenbo Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add unified luminance target (ablation) | LUCE · LOL-v2 | PSNR: 19.70 -> 20.21 | Improved |
| add unified luminance target (ablation) | LUCE · LOL-v2 | SSIM: 0.832 -> 0.840 | Improved |
| add unified luminance target (ablation) | LUCE · Unpaired (LIME, NPE, MEF, DICM, VV) | BRISQUE: 20.71 -> 18.03 | Improved |
| add unified luminance target (ablation) | LUCE · Unpaired (LIME, NPE, MEF, DICM, VV) | NL: 1.45 -> 0.76 | Improved |
| add curve mapping module (ablation) | LUCE · LOL-v2 | PSNR: 19.85 -> 20.21 | Improved |
| add curve mapping module (ablation) | LUCE · LOL-v2 | LPIPS: 0.200 -> 0.192 | Improved |
| add curve mapping module (ablation) | LUCE · Unpaired (LIME, NPE, MEF, DICM, VV) | BRISQUE: 19.86 -> 18.03 | Improved |
| add chromatic decoupling (ablation) | LUCE · LOL-v2 | LPIPS: 0.208 -> 0.192 | Improved |
| add chromatic decoupling (ablation) | LUCE · Unpaired (LIME, NPE, MEF, DICM, VV) | NL: 1.08 -> 0.76 | Improved |
| add chromatic decoupling (ablation) | LUCE · Unpaired (LIME, NPE, MEF, DICM, VV) | BRISQUE: 19.03 -> 18.03 | Improved |
| use LUCE single curve-domain energy instead of AGLLDiff multi-loss guidance | AGLLDiff · LSRW | PSNR: 16.92 -> 18.80 | Improved |
| use LUCE instead of AGLLDiff | AGLLDiff · LOL-v1 | PSNR: 21.81 -> 22.81 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- AGLLDiff — AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement (AAAI 2025) · better on 10 of 12 shared results
- LightenDiffusion — LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models (ECCV 2024) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination Enhancement (NeurIPS 2025 · similarity 0.88)
- Efficient Diffusion as Low Light Enhancer (CVPR 2025 · similarity 0.88)
- AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement (AAAI 2025 · similarity 0.87)
- Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models (AAAI 2025 · similarity 0.87)
- Zero-Reference Low-Light Enhancement via Physical Quadruple Priors (CVPR 2024 · similarity 0.86)
- Fourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
