Research map / Image generation / Image restoration
PASD: A Pixel-Adaptive Swarm Dynamics Approach for Unsupervised Low-Light Image Enhancement
Shuai Jin, Yuhua Qian, Feijiang Li, Guoqing Liu, Xinyan Liang
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 PASD instead of best unsupervised baseline | CUE · LOL-v1 | PSNR/SSIM: +0.04 SSIM and +0.23 dB PSNR | Improved |
| use PASD on unseen LOL-v2-real after training on LOL-v1 | unsupervised baselines · LOL-v2-real | PSNR: nearly 1 dB in PSNR | Improved |
| PASD on LOL-v2-syn and MEF | PASD · LOL-v2-syn / MEF | PSNR / NIQE | No clear effect |
| enhance images with PASD before YOLOv3 | Zero-DCE++ · ExDark | mean detection score: 58.14 -> 58.44 | Improved |
| add 8-connected neighborhood constraint L_p-8 (ablation) | PASD · LOL-v1 | visual quality | Improved |
| add cross-channel constraint L_p-rgb (ablation) | PASD · LOL-v1 | visual quality | Improved |
| add rate alignment protocol L_a (ablation) | PASD · LOL-v1 | visual quality | Improved |
| add multilevel neighborhood reward (ablation) | PASD · LOL-v1 | visual quality | Improved |
Closest papers by meaning
- Aesthetics-Guided Low-Light Enhancement (TPAMI 2025 · similarity 0.85)
- AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement (AAAI 2025 · similarity 0.83)
- Continuous Exposure Learning for Low-light Image Enhancement using Neural ODEs (ICLR 2025 · similarity 0.83)
- Multi-Domain Multi-Scale Diffusion Model for Low-Light Image Enhancement (AAAI 2024 · similarity 0.83)
- Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination Enhancement (NeurIPS 2025 · similarity 0.82)
- InstaRevive: One-Step Image Enhancement via Dynamic Score Matching (ICLR 2025 · similarity 0.82)
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.
