Papers › Enhancing Low-Light Images with Kolmogorov–Arnold Networks in Transformer Attention

Enhancing Low-Light Images with Kolmogorov–Arnold Networks in Transformer Attention

7 Nov 2024Sensors 2024 11archive 2025-07-28

Alexandru Brateanu, Raul Balmez, Ciprian Orhei, Cosmin Ancuti, Codruta Ancuti

Low-light image enhancement (LLIE) techniques improve the performance of image sensors by enhancing visibility and details in poorly lit environments and have significantly benefited from recent research into Transformer models. This work presents a novel Transformer attention mechanism inspired by the Kolmogorov–Arnold representation theorem, incorporating learnable non-linearity and multivariate function decomposition. This innovative mechanism is the foundation of KAN-𝒯, our proposed Transformer network. By enhancing feature flexibility and enabling the model to capture broader contextual information, KAN-𝒯 achieves superior performance. Our comprehensive experiments, both quantitative and qualitative, demonstrate that the proposed method achieves state-of-the-art performance in low-light image enhancement, highlighting its effectiveness and wide-ranging applicability. The code will be released upon publication.

PaperPDFCode

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

Image EnhancementKolmogorov-Arnold NetworksLow-Light Image Enhancement

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Low-Light Image Enhancement LOL KAN-T Average PSNR 27.18 #8 of 40 Archive leaderboard report
Low-Light Image Enhancement LOL KAN-T Params (M) 2.80 #8 of 40 Archive leaderboard report
Low-Light Image Enhancement LOL KAN-T SSIM 0.864 #8 of 40 Archive leaderboard report
Low-Light Image Enhancement LOLv2 KAN-T Average PSNR 28.87 #3 of 12 Archive leaderboard report
Low-Light Image Enhancement LOLv2 KAN-T SSIM 0.890 #3 of 12 Archive leaderboard report
Low-Light Image Enhancement LOLv2-synthetic KAN-T Average PSNR 29.77 #3 of 9 Archive leaderboard report
Low-Light Image Enhancement LOLv2-synthetic KAN-T SSIM 0.949 #3 of 9 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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