Towards Perfection: Building Inter-component Mutual Correction for Retinex-based Low-light Image Enhancement

TL;DR

This paper introduces IRetinex, a novel method that reduces inter-component residuals in Retinex-based low-light image enhancement, leading to more accurate decomposition and higher quality enhanced images.

Contribution

The paper proposes a new inter-correction Retinex model with modules to reduce residuals between illumination and reflectance, improving enhancement results.

Findings

Outperforms state-of-the-art methods on three benchmarks.

Effectively reduces inter-component residuals during decomposition.

Achieves higher quantitative and qualitative enhancement quality.

Abstract

In low-light image enhancement, Retinex-based deep learning methods have garnered significant attention due to their exceptional interpretability. These methods decompose images into mutually independent illumination and reflectance components, allows each component to be enhanced separately. In fact, achieving perfect decomposition of illumination and reflectance components proves to be quite challenging, with some residuals still existing after decomposition. In this paper, we formally name these residuals as inter-component residuals (ICR), which has been largely underestimated by previous methods. In our investigation, ICR not only affects the accuracy of the decomposition but also causes enhanced components to deviate from the ideal outcome, ultimately reducing the final synthesized image quality. To address this issue, we propose a novel Inter-correction Retinex model (IRetinex) to alleviate ICR during the decomposition and enhancement stage. In the decomposition stage, we leverage inter-component residual reduction module to reduce the feature similarity between illumination and reflectance components. In the enhancement stage, we utilize the feature similarity between the two components to detect and mitigate the impact of ICR within each enhancement unit. Extensive experiments on three low-light benchmark datasets demonstrated that by reducing ICR, our method outperforms state-of-the-art approaches both qualitatively and quantitatively.