Research map / Image generation / Image restoration
Nonlocal Retinex-Based Variational Model and its Deep Unfolding Twin for Low-Light Image Enhancement
Daniel Torres, Joan Duran, Julia Navarro, Catalina Sbert
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 |
|---|---|---|---|
| use CARNet instead of ResNet (ablation) | Unfolding method · LOLv1 | PSNR: 21.27 -> 22.98 | Improved |
| use CARNet instead of ResNet (ablation) | Unfolding method · LOLv1 | LPIPS: 0.163 -> 0.108 | Improved |
| use CARNet instead of ResNet (ablation) | Unfolding method · LOLv1 | SSIM: 0.8958 -> 0.9404 | Improved |
| add noise component N to the decomposition (ablation) | Variational model · qualitative | visual noise | Improved |
| add color correction pre-processing (ablation) | Variational model · qualitative | color balance | Improved |
| use nonlocal TV for reflectance and TV for illumination instead of Tikhonov illumination and TV reflectance (ablation) | Variational model · qualitative | sharpness and noise | Improved |
| use nonlocal gradient-fidelity constraint instead of local variant or none (ablation) | Variational model · qualitative | edge contrast | Improved |
| use unfolding model instead of variational model | Ours · LOLv1 | PSNR: 21.28 -> 22.98 | Improved |
| use variational model instead of unfolding model | Ours · LIME | NIQE: 3.5649 -> 3.4136 | Improved |
| use unfolding model vs Retinexformer | Ours-Unfolding · LOLv2-Synthetic | PSNR: 24.76 -> 24.39 | Hurt |
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.
- Retinexformer — Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement (ICCV 2023) · better on 5 of 7 shared results
- URetinexNet++ — URetinex-Net: Retinex-Based Deep Unfolding Network for Low-Light Image Enhancement (CVPR 2022) · better on 7 of 7 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
- IniRetinex: Rethinking Retinex-type Low-Light Image Enhancer via Initialization Perspective (AAAI 2025 · similarity 0.90)
- Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios (ICLR 2025 · similarity 0.88)
- MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space (NeurIPS 2024 · similarity 0.87)
- Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models (AAAI 2025 · similarity 0.87)
- Enhancing Low-Light Images: A Synthetic Data Perspective on Practical and Generalizable Solutions (AAAI 2025 · similarity 0.87)
- Zero-Reference Low-Light Enhancement via Physical Quadruple Priors (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.
