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

TL;DR

This paper introduces FSIDNet, a two-stage deep learning model that enhances low-light images by integrating frequency and spatial domain information through specialized interaction blocks and an information exchange module.

Contribution

The novel two-stage architecture with frequency-spatial interaction blocks and an information exchange module effectively improves low-light image enhancement performance.

Findings

Achieves superior visual quality and quantitative metrics on benchmark datasets.

Effectively propagates and flows information across stages and scales.

Preserves model efficiency while enhancing low-light images.

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.