Papers › Learning a Simple Low-Light Image Enhancer From Paired Low-Light Instances
Learning a Simple Low-Light Image Enhancer From Paired Low-Light Instances
Zhenqi Fu, Yan Yang, Xiaotong Tu, Yue Huang, Xinghao Ding, Kai-Kuang Ma
Low-light Image Enhancement (LIE) aims at improving contrast and restoring details for images captured in low-light conditions. Most of the previous LIE algorithms adjust illumination using a single input image with several handcrafted priors. Those solutions, however, often fail in revealing image details due to the limited information in a single image and the poor adaptability of handcrafted priors. To this end, we propose PairLIE, an unsupervised approach that learns adaptive priors from low-light image pairs. First, the network is expected to generate the same clean images as the two inputs share the same image content. To achieve this, we impose the network with the Retinex theory and make the two reflectance components consistent. Second, to assist the Retinex decomposition, we propose to remove inappropriate features in the raw image with a simple self-supervised mechanism. Extensive experiments on public datasets show that the proposed PairLIE achieves comparable performance against the state-of-the-art approaches with a simpler network and fewer handcrafted priors. Code is available at: https://github.com/zhenqifu/PairLIE.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Low-Light Image Enhancement | DICM | PairLIE | BRISQUE | 33.31 | #3 of 6 | Archive leaderboard | report |
| Low-Light Image Enhancement | DICM | PairLIE | NIQE | 4.03 | #3 of 6 | Archive leaderboard | report |
| Low-Light Image Enhancement | LIME | PairLIE | BRISQUE | 25.23 | #4 of 6 | Archive leaderboard | report |
| Low-Light Image Enhancement | LIME | PairLIE | NIQE | 4.58 | #4 of 6 | Archive leaderboard | report |
| Low-Light Image Enhancement | MEF | PairLIE | BRISQUE | 27.53 | #4 of 7 | Archive leaderboard | report |
| Low-Light Image Enhancement | MEF | PairLIE | NIQE | 4.06 | #4 of 7 | Archive leaderboard | report |
| Low-Light Image Enhancement | NPE | PairLIE | BRISQUE | 28.27 | #3 of 6 | Archive leaderboard | report |
| Low-Light Image Enhancement | NPE | PairLIE | NIQE | 4.18 | #3 of 6 | Archive leaderboard | report |
| Low-Light Image Enhancement | VV | PairLIE | BRISQUE | 39.13 | #3 of 7 | Archive leaderboard | report |
| Low-Light Image Enhancement | VV | PairLIE | NIQE | 3.57 | #3 of 7 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections