Papers › GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval

GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval

17 Jul 2024arXiv:2407.12431archive 2025-07-28

Han Zhou, Wei Dong, Xiaohong Liu, Shuaicheng Liu, Xiongkuo Min, Guangtao Zhai, Jun Chen

Most existing Low-light Image Enhancement (LLIE) methods either directly map Low-Light (LL) to Normal-Light (NL) images or use semantic or illumination maps as guides. However, the ill-posed nature of LLIE and the difficulty of semantic retrieval from impaired inputs limit these methods, especially in extremely low-light conditions. To address this issue, we present a new LLIE network via Generative LAtent feature based codebook REtrieval (GLARE), in which the codebook prior is derived from undegraded NL images using a Vector Quantization (VQ) strategy. More importantly, we develop a generative Invertible Latent Normalizing Flow (I-LNF) module to align the LL feature distribution to NL latent representations, guaranteeing the correct code retrieval in the codebook. In addition, a novel Adaptive Feature Transformation (AFT) module, featuring an adjustable function for users and comprising an Adaptive Mix-up Block (AMB) along with a dual-decoder architecture, is devised to further enhance fidelity while preserving the realistic details provided by codebook prior. Extensive experiments confirm the superior performance of GLARE on various benchmark datasets and real-world data. Its effectiveness as a preprocessing tool in low-light object detection tasks further validates GLARE for high-level vision applications. Code is released at https://github.com/LowLevelAI/GLARE.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

lowlevelai/glare officialmentioned in papermentioned on GitHubpytorch report

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

DecoderImage EnhancementLow-Light Image EnhancementObject DetectionQuantizationRetrievalSemantic Retrievalobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Low-Light Image Enhancement LOL GLARE Average PSNR 27.35 #5 of 40 Archive leaderboard report
Low-Light Image Enhancement LOL GLARE LPIPS 0.083 #5 of 40 Archive leaderboard report
Low-Light Image Enhancement LOL GLARE SSIM 0.883 #5 of 40 Archive leaderboard report
Low-Light Image Enhancement LOL GLARE SSIM (sRGB) 0.883 #5 of 40 Archive leaderboard report
Low-Light Image Enhancement LOLv2 GLARE Average PSNR 28.98 #2 of 12 Archive leaderboard report
Low-Light Image Enhancement LOLv2 GLARE LPIPS 0.097 #2 of 12 Archive leaderboard report
Low-Light Image Enhancement LOLv2 GLARE SSIM 0.905 #2 of 12 Archive leaderboard report
Low-Light Image Enhancement LOLv2-synthetic GLARE Average PSNR 29.84 #2 of 9 Archive leaderboard report
Low-Light Image Enhancement LOLv2-synthetic GLARE SSIM 0.958 #2 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

ALIGN

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