Papers › TreEnhance: A Tree Search Method For Low-Light Image Enhancement
TreEnhance: A Tree Search Method For Low-Light Image Enhancement
Marco Cotogni, Claudio Cusano
In this paper we present TreEnhance, an automatic method for low-light image enhancement capable of improving the quality of digital images. The method combines tree search theory, and in particular the Monte Carlo Tree Search (MCTS) algorithm, with deep reinforcement learning. Given as input a low-light image, TreEnhance produces as output its enhanced version together with the sequence of image editing operations used to obtain it. During the training phase, the method repeatedly alternates two main phases: a generation phase, where a modified version of MCTS explores the space of image editing operations and selects the most promising sequence, and an optimization phase, where the parameters of a neural network, implementing the enhancement policy, are updated. Two different inference solutions are proposed for the enhancement of new images: one is based on MCTS and is more accurate but more time and memory consuming; the other directly applies the learned policy and is faster but slightly less precise. As a further contribution, we propose a guided search strategy that "reverses" the enhancement procedure that a photo editor applied to a given input image. Unlike other methods from the state of the art, TreEnhance does not pose any constraint on the image resolution and can be used in a variety of scenarios with minimal tuning. We tested the method on two datasets: the Low-Light dataset and the Adobe Five-K dataset obtaining good results from both a qualitative and a quantitative point of view.
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 |
|---|---|---|---|---|---|---|---|
| Image Enhancement | MIT-Adobe FiveK | TreEnhance | DeltaE | 11.25 | #1 of 1 | Archive leaderboard | report |
| Image Enhancement | MIT-Adobe FiveK | TreEnhance | LPIPS | 0.06 | #1 of 1 | Archive leaderboard | report |
| Image Enhancement | MIT-Adobe FiveK | TreEnhance | PSNR | 21.24 | #1 of 1 | Archive leaderboard | report |
| Image Enhancement | MIT-Adobe FiveK | TreEnhance | SSIM | 0.89 | #1 of 1 | Archive leaderboard | report |
| Low-Light Image Enhancement | LOL | TreEnhance | Average PSNR | 21.96 | #34 of 40 | Archive leaderboard | report |
| Low-Light Image Enhancement | LOL | TreEnhance | SSIM | 0.81 | #34 of 40 | 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.
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