DMFourLLIE: Dual-Stage and Multi-Branch Fourier Network for Low-Light Image Enhancement

TL;DR

DMFourLLIE introduces a dual-stage, multi-branch Fourier network that enhances low-light images by effectively leveraging phase and amplitude information, leading to superior detail preservation and color accuracy.

Contribution

The paper proposes a novel dual-stage, multi-branch Fourier framework that emphasizes phase information and integrates infrared guidance for improved low-light image enhancement.

Findings

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

Effectively preserves spatial structures and textures

Reduces color distortions and noise

Abstract

In the Fourier frequency domain, luminance information is primarily encoded in the amplitude component, while spatial structure information is significantly contained within the phase component. Existing low-light image enhancement techniques using Fourier transform have mainly focused on amplifying the amplitude component and simply replicating the phase component, an approach that often leads to color distortions and noise issues. In this paper, we propose a Dual-Stage Multi-Branch Fourier Low-Light Image Enhancement (DMFourLLIE) framework to address these limitations by emphasizing the phase component's role in preserving image structure and detail. The first stage integrates structural information from infrared images to enhance the phase component and employs a luminance-attention mechanism in the luminance-chrominance color space to precisely control amplitude enhancement. The second stage combines multi-scale and Fourier convolutional branches for robust image reconstruction, effectively recovering spatial structures and textures. This dual-branch joint optimization process ensures that complex image information is retained, overcoming the limitations of previous methods that neglected the interplay between amplitude and phase. Extensive experiments across multiple datasets demonstrate that DMFourLLIE outperforms current state-of-the-art methods in low-light image enhancement. Our code is available at https://github.com/bywlzts/DMFourLLIE.