Research map / Image generation / Image restoration
URetinex-Net: Retinex-Based Deep Unfolding Network for Low-Light Image Enhancement
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use URetinex-Net rather than the strongest listed baseline | Low-light enhancement · LOL | PSNR: 21.3003 -> 21.3282 | Helped |
| Use URetinex-Net rather than the strongest listed baseline | Low-light enhancement · LOL | MAE: 0.0679 -> 0.0832 | Hurt |
| Use URetinex-Net rather than the strongest listed baseline | Low-light enhancement · LOL | SSIM: 0.8226 -> 0.8348 | Helped |
| Use URetinex-Net rather than the strongest listed baseline | Low-light enhancement · LOL | LPIPS: 1.4091 -> 1.2234 | Helped |
| Use URetinex-Net rather than the strongest listed baseline | Low-light enhancement · SICE | PSNR: 18.5942 -> 18.9467 | Helped |
| Use URetinex-Net rather than the strongest listed baseline | Low-light enhancement · SICE | MAE: 0.1060 -> 0.1068 | Hurt |
| Use URetinex-Net rather than the strongest listed baseline | Low-light enhancement · SICE | SSIM: 0.7762 -> 0.7808 | Helped |
| Use URetinex-Net rather than the strongest listed baseline | Low-light enhancement · SICE | LPIPS: 1.2613 -> 1.2744 | Hurt |
| Add the data-dependent initialization module (ablation) | URetinex-Net · LOL | PSNR: 20.0992 -> 21.3282 | Helped |
| Add unfolding optimization instead of simply stacking GR and GL networks (ablation) | URetinex-Net · LOL | PSNR: 20.7572 -> 21.3282 | Helped |
| Add illumination guidance to the GR input (ablation) | URetinex-Net · LOL | PSNR: 19.6109 -> 21.3282 | Helped |
| Use 3 unfolding stages instead of 1 (ablation) | URetinex-Net · LOL | PSNR: 20.1222 -> 21.3282 | Helped |
Closest papers by meaning
- IniRetinex: Rethinking Retinex-type Low-Light Image Enhancer via Initialization Perspective (AAAI 2025 · similarity 0.91)
- Dehaze-RetinexGAN: Real-World Image Dehazing via Retinex-based Generative Adversarial Network (AAAI 2025 · similarity 0.87)
- DPLUT: Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors (AAAI 2025 · similarity 0.86)
- Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios (ICLR 2025 · similarity 0.86)
- MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space (NeurIPS 2024 · similarity 0.86)
- Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models (AAAI 2025 · similarity 0.85)
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.