Research map / Image generation / Image restoration
Noise Self-Regression: A New Learning Paradigm to Enhance Low-Light Images Without Task-Related Data
Zhao Zhang, Suiyi Zhao, Xiaojie Jin, Mingliang Xu, Yi Yang, Shuicheng Yan, Meng Wang
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 |
|---|---|---|---|
| shift noise mean (MS-NoiSER) instead of zero-mean (ablation) | NoiSER · Average PSNR (LOL, LSRW) | PSNR: 16.100 -> 16.328 | Improved |
| shift noise mean (MS-NoiSER) (ablation) | NoiSER · LSRW (Huawei) | PSNR: 15.726 -> 16.674 | Improved |
| shift noise mean (MS-NoiSER) (ablation) | NoiSER · LOL | PSNR: 17.574 -> 17.194 | Hurt |
| shift noise mean (MS-NoiSER) (ablation) | NoiSER · LSRW (Nikon) | PSNR: 15.553 -> 15.158 | Hurt |
| use early stopping instead of full convergence (ablation) | NoiSER · LOL | PSNR: 17.5748 -> 17.0250 | Hurt |
| raise noise variance to 3 (Var3) (ablation) | NoiSER-ES · LOL | NIQE: 3.7206 -> 3.6806 | Improved |
| raise noise variance to 3 (Var3) (ablation) | NoiSER-ES · LOL | PSNR: 17.0250 -> 14.9257 | Hurt |
| add instance normalization layer (ablation) | NoiSER · LOL visual | visual quality | Improved |
| add TV regularization (ablation) | NoiSER-Var3 · LOL visual | visual noise | Improved |
| use 3x3 instead of 1x1 convolution (ablation) | NoiSER · LOL visual | visual quality | Improved |
| increase noise standard deviation (ablation) | NoiSER · LOL visual | brightness | Mixed |
| use full NoiSER instead of instance normalization alone (ablation) | IN only · LOL visual | visual quality | Improved |
Closest papers by meaning
- Enhancing Low-Light Images: A Synthetic Data Perspective on Practical and Generalizable Solutions (AAAI 2025 · similarity 0.90)
- Learnable Feature Patches and Vectors for Boosting Low-light Image Enhancement without External Knowledge (ICCV 2025 · similarity 0.90)
- Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models (AAAI 2025 · similarity 0.89)
- DarkIR: Robust Low-Light Image Restoration (CVPR 2025 · similarity 0.88)
- DPLUT: Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors (AAAI 2025 · similarity 0.87)
- IniRetinex: Rethinking Retinex-type Low-Light Image Enhancer via Initialization Perspective (AAAI 2025 · similarity 0.87)
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.
