Research map / Image generation / Image restoration
ICLR: Inter-Chrominance and Luminance Interaction for Natural Color Restoration in Low-Light Image Enhancement
Xin Xu, Hao Liu, Wei Liu, Wei Wang, Jiayi Wu, Kui Jiang
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 MAFM (multidimensional attention-guided fusion) (ablation) | ICLR · LOLv1 | PSNR: 28.028 -> 28.603 | Improved |
| use CDEM instead of traditional cross attention (ablation) | ICLR · LOLv1 | PSNR: 27.998 -> 28.603 | Improved |
| use Covariance Correction Loss instead of L1 (ablation) | ICLR · LOLv1 | PSNR: 28.202 -> 28.603 | Improved |
| use Covariance Correction Loss instead of L2 (ablation) | ICLR · LOLv1 | PSNR: 28.275 -> 28.603 | Improved |
| use two MAFMs instead of only the one before DIEM (ablation) | ICLR · LOLv1 | PSNR: 28.335 -> 28.603 | Improved |
| use two MAFMs instead of only the one after DIEM (ablation) | ICLR · LOLv1 | PSNR: 28.372 -> 28.603 | Improved |
| add MAFM (ablation) | ICLR · LOLv1 | LPIPS: 0.080 -> 0.068 | Improved |
| use CCL instead of pixel-wise loss on low-covariance images (ablation) | ICLR · New synthetic dataset (215 pairs) | PSNR | Improved |
| ICLR vs CIDNet on unpaired MEF NIQE | ICLR · MEF | NIQE | Hurt |
| ICLR parameter count vs URWKV and CIDNet | ICLR · model size | Params (M): 1.88 (CIDNet) -> 4.27 | Hurt |
| ICLR vs Retinexformer on LOLv2-Syn LPIPS | ICLR · LOLv2-Syn | LPIPS: 0.189 (Retinexformer) vs 0.217 | 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.
- URWKV — URWKV: Unified RWKV Model with Multi-state Perspective for Low-light Image Restoration (CVPR 2025) · better on 3 of 4 shared results
- Retinexformer — Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement (ICCV 2023) · better on 2 of 3 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
- HVI: A New Color Space for Low-light Image Enhancement (CVPR 2025 · similarity 0.86)
- Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination Enhancement (NeurIPS 2025 · similarity 0.85)
- Enhancing Low-Light Images: A Synthetic Data Perspective on Practical and Generalizable Solutions (AAAI 2025 · similarity 0.85)
- Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios (ICLR 2025 · similarity 0.84)
- ChromaFusionNet (CFNet): Natural Fusion of Fine-Grained Color Editing (AAAI 2024 · similarity 0.84)
- Unveiling Details in the Dark: Simultaneous Brightening and Zooming for Low-Light Image Enhancement (AAAI 2024 · similarity 0.84)
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.
