Frequency-Spatial Interaction Driven Network for Low-Light Image Enhancement

TL;DR

The paper tackles low-light image enhancement by addressing two gaps: underutilization of Fourier-domain information and weak information propagation in multi-stage networks. It introduces FSIDNet, a two-stage LLIE framework that first restores amplitude to boost brightness and then refines phase to enhance structure, using two specialized frequency-spatial blocks (FSIA and FSIP) for mutual fusion of frequency and spatial cues. An Information Exchange Module (IEM) couples the stages through cross-scale and cross-stage fusion, including a Dynamic Filter Block that generates content-adaptive, per-pixel filters to bolster representation. Experimental results on multiple LLIE benchmarks and unpaired datasets show that FSIDNet achieves state-of-the-art PSNR/SSIM and competitive NIQE while maintaining efficiency, validating the effectiveness of frequency-spatial interaction and cross-stage information exchange for LLIE.

Abstract

Low-light image enhancement (LLIE) aims at improving the perception or interpretability of an image captured in an environment with poor illumination. With the advent of deep learning, the LLIE technique has achieved significant breakthroughs. However, existing LLIE methods either ignore the important role of frequency domain information or fail to effectively promote the propagation and flow of information, limiting the LLIE performance. In this paper, we develop a novel frequency-spatial interaction-driven network (FSIDNet) for LLIE based on two-stage architecture. To be specific, the first stage is designed to restore the amplitude of low-light images to improve the lightness, and the second stage devotes to restore phase information to refine fine-grained structures. Considering that Frequency domain and spatial domain information are complementary and both favorable for LLIE, we further develop two frequency-spatial interaction blocks which mutually amalgamate the complementary spatial and frequency information to enhance the capability of the model. In addition, we construct the Information Exchange Module (IEM) to associate two stages by adequately incorporating cross-stage and cross-scale features to effectively promote the propagation and flow of information in the two-stage network structure. Finally, we conduct experiments on several widely used benchmark datasets (i.e., LOL-Real, LSRW-Huawei, etc.), which demonstrate that our method achieves the excellent performance in terms of visual results and quantitative metrics while preserving good model efficiency.

Figures (1)

• Figure 1: The proposed FSIDNet Network.