Research map / Image generation / Image restoration
EEMEFN: Low-Light Image Enhancement via Edge-Enhanced Multi-Exposure Fusion Network
Minfeng Zhu, Pingbo Pan, Wei Chen, Yi Yang
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 |
|---|---|---|---|
| generate and fuse multi-exposure images (MEF vs concatenated baseline) (ablation) | U-net · SID Sony | PSNR: 29.06 -> 29.43 | Improved |
| add edge enhancement module (ablation) | MEF · SID Sony | PSNR: 29.43 -> 29.60 | Improved |
| EEMEFN vs Chen et al. U-net | low-light enhancement · SID Fuji | PSNR: 26.61 -> 27.38 | Improved |
| EEMEFN vs Chen et al. U-net | low-light enhancement · SID Sony | LPIPS: 0.476 -> 0.458 | Improved |
| add fusion blocks with max+avg (vs basic late-fusion MEF) (ablation) | MEF · SID Sony | PSNR: 29.18 -> 29.43 | Improved |
| combine max and avg in fusion block vs avg only (ablation) | MEF · SID Sony | PSNR: 29.30 -> 29.43 | Improved |
| include exposure ratio 1 in set ({1,k*/2} vs {k*/2,k*}) (ablation) | MEF · SID Sony | PSNR: 29.27 -> 29.43 | Improved |
| use three exposure ratios instead of two (ablation) | EEMEFN · SID Sony | PSNR: 29.60 -> 29.56 | No clear effect |
| replace EE module with edge-preserving loss (ablation) | MEF · SID Sony | PSNR: 29.43 -> 28.44 | Hurt |
| feed initial image to EE module (ablation) | EEMEFN · SID Sony | PSNR: 29.15 -> 29.60 | Improved |
| feed multi-exposure images to EE module (ablation) | EEMEFN · SID Sony | PSNR: 29.56 -> 29.60 | Improved |
Later papers that compared with this method
1 later accepted paper reports EEMEFN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- DNF: Decouple and Feedback Network for Seeing in the Dark (CVPR 2023 · better on 2 of 2 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
- Attention Guided Low-Light Image Enhancement with a Large Scale Low-Light Simulation Dataset (IJCV 2021 · similarity 0.87)
- Low-Light Image Enhancement Network Based on Multi-Scale Feature Complementation (AAAI 2023 · similarity 0.87)
- Multinex: Lightweight Low-light Image Enhancement via Multi-prior Retinex (CVPR 2026 · similarity 0.87)
- Zero-Shot Low-Light Image Enhancement via Latent Diffusion Models (AAAI 2025 · similarity 0.87)
- Low-Light Image and Video Enhancement Using Deep Learning: A Survey (TPAMI 2021 · similarity 0.86)
- DPLUT: Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors (AAAI 2025 · 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.
