Self-supervised unfolding network with shared reflectance learning for low-light image enhancement

Liu, Jia, Luo, Yu, Yue, Guanghui, Ling, Jie, Liao, Liang, Lin, Chia-Wen, Zhai, Guangtao and Zhou, Wei 2026. Self-supervised unfolding network with shared reflectance learning for low-light image enhancement. IEEE Transactions on Image Processing 10.1109/tip.2026.3652021

Full text not available from this repository.

Abstract

Recently, incorporating Retinex theory with unfolding networks has attracted increasing attention in the low-light image enhancement field. However, existing methods have two limitations, i.e., ignoring the modeling of the physical prior of Retinex theory and relying on a large amount of paired data. To advance this field, we propose a novel self-supervised unfolding network, named S2UNet, for the LIE task. Specifically, we formulate a novel optimization model based on the principle that content-consistent images under different illumination should share the same reflectance. The model simultaneously decomposes two illumination-different images into a shared reflectance component and two independent illumination components. Due to the absence of the normal-light image, we process the low-light image with gamma correction to create the illumination-different image pair. Then, we translate this model into a multi-stage unfolding network, in which each stage alternately optimizes the shared reflectance component and the respective illumination components of the two images. During progressive multi-stage optimization, the network inherently encodes the reflectance consistency prior by jointly estimating an optimal reflectance across varying illumination conditions. Finally, considering the presence of noise in low-light images and to suppress noise amplification, we propose a self-supervised denoising mechanism. Extensive experiments on nine benchmark datasets demonstrate that our proposed S2UNet outperforms state-of-the-art unsupervised methods in terms of both quantitative metrics and visual quality, while achieving competitive performance compared to supervised methods. The source code will be available at https: //github.com/J-Liu-DL/S2UNet.

Item Type:	Article
Date Type:	Published Online
Status:	In Press
Schools:	Schools > Computer Science & Informatics
Publisher:	Institute of Electrical and Electronics Engineers (IEEE)
ISSN:	1057-7149
Last Modified:	19 Jan 2026 14:30
URI:	https://orca.cardiff.ac.uk/id/eprint/184022

Actions (repository staff only)

Edit Item