Research map / Image generation / Image restoration
Learning to See in the Extremely Dark
Hai Jiang, Binhao Guan, Zhen Liu, Xiaohong Liu, Jian Yu, Zheng Liu, Songchen Han, Shuaicheng Liu
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 multi-stage training instead of single-stage joint training (ablation) | SIED diffusion framework · SIED Canon 0.01-0.1 lux | PSNR: 22.96 -> 24.85 | Improved |
| use multi-stage training instead of single-stage joint training (ablation) | SIED diffusion framework · SIED Canon 0.01-0.1 lux | LPIPS: 0.431 -> 0.360 | Improved |
| add Adaptive Illumination Correction Module (ablation) | SIED diffusion framework · SIED Canon 0.01-0.1 lux | PSNR: 23.23 -> 24.85 | Improved |
| add AICM (ablation) | SIED diffusion framework · SIED Canon 0.01-0.1 lux | SSIM: 0.839 -> 0.849 | Improved |
| add AICM (ablation) | SIED diffusion framework · SIED Canon 0.01-0.1 lux | LPIPS: 0.378 -> 0.360 | Improved |
| use AICM instead of fixed amplification factor 100 (ablation) | SIED diffusion framework · SIED Canon 0.01-0.1 lux | PSNR: 23.74 -> 24.85 | Improved |
| use AICM instead of fixed amplification factor 200 (ablation) | SIED diffusion framework · SIED Canon 0.01-0.1 lux | PSNR: 23.48 -> 24.85 | Improved |
| use AICM instead of fixed amplification factor 300 (ablation) | SIED diffusion framework · SIED Canon 0.01-0.1 lux | PSNR: 23.18 -> 24.85 | Improved |
| add color consistency loss (ablation) | SIED diffusion framework · SIED Canon 0.01-0.1 lux | PSNR: 24.53 -> 24.85 | Improved |
| add color consistency loss (ablation) | SIED diffusion framework · SIED Canon 0.01-0.1 lux | SSIM: 0.836 -> 0.849 | Improved |
| add color consistency loss (ablation) | SIED diffusion framework · SIED Canon 0.01-0.1 lux | LPIPS: 0.389 -> 0.360 | Improved |
| multi-stage framework vs single-stage competitors | Multi-stage methods · SIED | PSNR/SSIM/LPIPS | Improved |
Closest papers by meaning
- Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models (AAAI 2025 · similarity 0.89)
- Zero-Reference Low-Light Enhancement via Physical Quadruple Priors (CVPR 2024 · similarity 0.88)
- Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination Enhancement (NeurIPS 2025 · similarity 0.88)
- Enhancing Low-Light Images: A Synthetic Data Perspective on Practical and Generalizable Solutions (AAAI 2025 · similarity 0.88)
- ZERO-IG: Zero-Shot Illumination-Guided Joint Denoising and Adaptive Enhancement for Low-Light Images (CVPR 2024 · similarity 0.87)
- Fourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring (CVPR 2024 · 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.
