ICLR: Inter-Chrominance and Luminance Interaction for Natural Color Restoration in Low-Light Image Enhancement

TL;DR

This paper introduces the ICLR framework, which enhances low-light image enhancement by modeling inter-chrominance and luminance interactions, effectively reducing errors and improving detail restoration.

Contribution

The paper proposes a novel ICLR framework with DIEM and CCL to better exploit chrominance-luminance interactions and address distributional differences in low-light image enhancement.

Findings

Outperforms state-of-the-art methods on multiple datasets

Improves chrominance and luminance feature extraction

Reduces chrominance errors through covariance correction

Abstract

Low-Light Image Enhancement (LLIE) task aims at improving contrast while restoring details and textures for images captured in low-light conditions. HVI color space has made significant progress in this task by enabling precise decoupling of chrominance and luminance. However, for the interaction of chrominance and luminance branches, substantial distributional differences between the two branches prevalent in natural images limit complementary feature extraction, and luminance errors are propagated to chrominance channels through the nonlinear parameter. Furthermore, for interaction between different chrominance branches, images with large homogeneous-color regions usually exhibit weak correlation between chrominance branches due to concentrated distributions. Traditional pixel-wise losses exploit strong inter-branch correlations for co-optimization, causing gradient conflicts in weakly correlated regions. Therefore, we propose an Inter-Chrominance and Luminance Interaction (ICLR) framework including a Dual-stream Interaction Enhancement Module (DIEM) and a Covariance Correction Loss (CCL). The DIEM improves the extraction of complementary information from two dimensions, fusion and enhancement, respectively. The CCL utilizes luminance residual statistics to penalize chrominance errors and balances gradient conflicts by constraining chrominance branches covariance. Experimental results on multiple datasets show that the proposed ICLR framework outperforms state-of-the-art methods.