Dual Degradation-Inspired Deep Unfolding Network for Low-Light Image Enhancement

TL;DR

This paper introduces DASUNet, a novel deep unfolding network inspired by dual degradation models, explicitly modeling luminance and chrominance deterioration for improved low-light image enhancement.

Contribution

It proposes a dual degradation model and an unfolding deep network with Transformer blocks and a space aggregation module, explicitly capturing physical degradation mechanisms.

Findings

DASUNet outperforms state-of-the-art methods on multiple datasets.

The dual degradation model effectively captures luminance and chrominance deterioration.

The space aggregation module enhances interaction between degradation models.

Abstract

Although low-light image enhancement has achieved great stride based on deep enhancement models, most of them mainly stress on enhancement performance via an elaborated black-box network and rarely explore the physical significance of enhancement models. Towards this issue, we propose a Dual degrAdation-inSpired deep Unfolding network, termed DASUNet, for low-light image enhancement. Specifically, we construct a dual degradation model (DDM) to explicitly simulate the deterioration mechanism of low-light images. It learns two distinct image priors via considering degradation specificity between luminance and chrominance spaces. To make the proposed scheme tractable, we design an alternating optimization solution to solve the proposed DDM. Further, the designed solution is unfolded into a specified deep network, imitating the iteration updating rules, to form DASUNet. Based on different specificity in two spaces, we design two customized Transformer block to model different priors. Additionally, a space aggregation module (SAM) is presented to boost the interaction of two degradation models. Extensive experiments on multiple popular low-light image datasets validate the effectiveness of DASUNet compared to canonical state-of-the-art low-light image enhancement methods. Our source code and pretrained model will be publicly available.