Research map / Image generation / Image restoration
DiffLLE: Diffusion-based Domain Calibration for Weak Supervised Low-light Image Enhancement
Shuzhou Yang, Xuanyu Zhang, Yinhuai Wang, Jiwen Yu, Yuhan Wang, Jian Zhang
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 FTD (fine-grained target domain distillation) (ablation) | DiffLLE · LOL | PSNR: 16.42 -> 22.24 | Improved |
| add FTD (ablation) | DiffLLE · LSRW | PSNR: 16.77 -> 18.63 | Improved |
| add FTD (ablation) | DiffLLE · LSRW | LOE: 272.4 -> 201.3 | Improved |
| add DDC (diffusion degradation calibration) on top of FTD (ablation) | DiffLLE trained on LSRW · LOL | PSNR: 17.25 -> 18.50 | Improved |
| add FTD without DDC (ablation) | DiffLLE trained on LSRW · LOL | PSNR: 16.89 -> 17.25 | Improved |
| add DDC (ablation) | DiffLLE trained on LSRW · LIME | NIQE: 4.17 -> 3.76 | Improved |
| add DDC to ZeroDCE (ablation) | ZeroDCE · DICM | NIQE: 3.61 -> 3.01 | Improved |
| add DDC to RUAS | RUAS · NPE | NIQE: 6.23 -> 3.91 | Improved |
| add DDC to EnGAN | EnGAN · MEF | NIQE: 3.13 -> 3.34 | Hurt |
| add FTD to EnGAN | EnGAN · LOL | PSNR: 18.13 -> 18.04 | Mixed |
| add FTD to PairLIE | PairLIE · LSRW | SSIM: 0.5009 -> 0.5340 | Improved |
| increase FTD iterations beyond 3 (ablation) | DiffLLE · LSRW | PSNR/SSIM | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- URetinexNet — URetinex-Net: Retinex-Based Deep Unfolding Network for Low-Light Image Enhancement (CVPR 2022) · better on 4 of 5 shared results
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
- Multi-Domain Multi-Scale Diffusion Model for Low-Light Image Enhancement (AAAI 2024 · similarity 0.86)
- AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement (AAAI 2025 · similarity 0.85)
- Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models (AAAI 2025 · similarity 0.84)
- Low-Light Image Enhancement via Generative Perceptual Priors (AAAI 2025 · similarity 0.84)
- Fourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring (CVPR 2024 · similarity 0.83)
- Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios (ICLR 2025 · similarity 0.83)
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.
