Research map / Image generation / Image restoration
Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement
Read the paperCheck 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 |
|---|---|---|---|
| Add SKF to LLFlow-L | LLFlow-L · LOL | PSNR: 24.999 -> 26.798 | Helped |
| Add SKF to LLFlow-L | LLFlow-L · LOL-v2 | PSNR: 26.200 -> 28.451 | Helped |
| Add SKF to LLFlow-L | LLFlow-L · LOL | NIQE: 5.582 -> 5.589 | Hurt |
| Add SKF to LLFlow-L | LLFlow-L · LOL-v2 | NIQE: 5.406 -> 5.725 | Hurt |
| Add SKF | HWMNet · LOL | PSNR: 24.240 -> 25.086 | Helped |
| Add SCH loss and SE module (ablation) | HWMNet · LOL | PSNR: 24.240 -> 25.123 | Helped |
| Add SCH loss, SA loss, and SE module (ablation) | HWMNet · LOL | PSNR: 24.240 -> 25.086 | Helped |
| Add SA loss to SCH loss and SE configuration (ablation) | HWMNet · LOL | PSNR: 25.123 -> 25.086 | Hurt |
| Use semantic-guided SA loss instead of classic global/local adversarial loss (ablation) | HWMNet with SCH loss · LOL | NIQE: 4.546 -> 4.311 | Helped |
| Increase model size without adding semantic priors (ablation) | HWMNet · LOL | PSNR: 24.240 -> 24.445 | Helped |
| Add SKF rather than only increasing model size (ablation) | HWMNet · LOL | PSNR: 24.445 -> 25.086 | Helped |
| Add SCH loss (ablation) | KinD++, DRBN, and HWMNet · LOL | PSNR: 19.170, 20.040, 24.590 | Helped |
Closest papers by meaning
- Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models (AAAI 2025 · similarity 0.88)
- Improving Visual and Downstream Performance of Low-Light Enhancer with Vision Foundation Models Collaboration (CVPR 2025 · similarity 0.87)
- Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination Enhancement (NeurIPS 2025 · similarity 0.86)
- Enhancing Low-Light Images: A Synthetic Data Perspective on Practical and Generalizable Solutions (AAAI 2025 · similarity 0.86)
- Zero-Reference Low-Light Enhancement via Physical Quadruple Priors (CVPR 2024 · similarity 0.85)
- Dispel Darkness for Better Fusion: A Controllable Visual Enhancer based on Cross-modal Conditional Adversarial Learning (CVPR 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.