Research map / Image generation / Image restoration
Low-light Image Enhancement via Breaking Down the Darkness
Xiaojie Guo, Qiming Hu
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 the denoising process (ablation) | Bread · LOL eval (ablation) | PSNR: 16.91 -> 22.92 | Improved |
| add the denoising process (ablation) | Bread · LOL eval (ablation) | SSIM: 0.586 -> 0.836 | Improved |
| add the noise fusion module (NFM) (ablation) | Bread · LOL eval (ablation) | PSNR: 17.08 -> 22.92 | Improved |
| add the noise fusion module (NFM) (ablation) | Bread · LOL eval (ablation) | SSIM: 0.721 -> 0.836 | Improved |
| add IA-NS separation (ablation) | Bread · LOL eval (ablation) | PSNR: 18.69 -> 22.92 | Improved |
| add IA-NS separation (ablation) | Bread · LOL eval (ablation) | SSIM: 0.785 -> 0.836 | Improved |
| use spatially-correlated Gaussian noise instead of fixed Gaussian noise (ablation) | Bread · LOL eval (ablation) | PSNR: 21.40 -> 22.92 | Improved |
| use spatially-correlated Gaussian noise instead of Poisson noise (ablation) | Bread · LOL eval (ablation) | PSNR: 22.44 -> 22.92 | Improved |
| use spatially-correlated Gaussian noise instead of Poisson noise (ablation) | Bread · LOL eval (ablation) | SSIM: 0.831 -> 0.836 | Improved |
| train color adaption net with multi-exposure data (Bread-ME) (ablation) | Bread · LOL eval (ablation) | PSNR: 22.92 -> 22.96 | Improved |
| train color adaption net with multi-exposure data (Bread-ME) (ablation) | Bread · LOL eval (ablation) | PSNR_C (gamma-corrected): 25.98 -> 26.06 | Improved |
| train color adaption net with multi-exposure data (Bread-ME) (ablation) | Bread · LOL eval (ablation) | SSIM_C (gamma-corrected): 0.851 -> 0.857 | Improved |
Closest papers by meaning
- Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios (ICLR 2025 · similarity 0.87)
- Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination Enhancement (NeurIPS 2025 · similarity 0.87)
- Unveiling Details in the Dark: Simultaneous Brightening and Zooming for Low-Light Image Enhancement (AAAI 2024 · similarity 0.86)
- Color Shift Estimation-and-Correction for Image Enhancement (CVPR 2024 · similarity 0.86)
- ZERO-IG: Zero-Shot Illumination-Guided Joint Denoising and Adaptive Enhancement for Low-Light Images (CVPR 2024 · similarity 0.85)
- Enhancing Low-Light Images: A Synthetic Data Perspective on Practical and Generalizable Solutions (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.
