Rethinking Low-Light Image Enhancement: A Log-Domain Intensity--Chromaticity Decoupling Perspective
Guangrui Bai, Yifan Mei, Yahui Deng, Yuhan Chen, Yuze Qiu, Wenhai Liu, Erbao Dong
cs.CV
Abstract
Explicit reconstruction constraints derived from the decoupled representation are further imposed to suppress abnormal channel amplification and chromatic noise. Experiments on LOLv2-Real, MIT-Adobe FiveK, and LSRW show that the proposed method achieves competitive or superior quantitative and visual performance, reaching 29.71 dB PSNR and 0.89 SSIM on LOLv2-Real. DarkFace experiments further indicate improved downstream face detection under low-light conditions. Code and pretrained models are available at: https://github.com/mubaisam/ICD.
Topics
Classified with taxonomy v2 on Wed, 2 Sept 2026.