Dual-Branch Low-Light Image Enhancement via Spatial and Multi-Scale Frequency Domain Fusion

Abstract

The images captured under extreme lighting conditions can exhibit severe image degradation, which significantly impacts the performance of downstream visual tasks. Existing deep learning-based approaches for low-light image enhancement have primarily focused on spatial domain enhancement while neglecting frequency domain information. Therefore, we introduce a novel network for low-light image enhancement that operates in both spatial and frequency domains (multi-scale pyramid and Fourier transform) simultaneously, named SMFNet. Our main idea involves using a dual-branch structure, incorporating spatial and multi-scale frequency domain branches. The spatial branch employs SpaBlock to extract image features, while the multi-scale frequency branch utilizes Laplacian pyramid and Fourier transform to extract frequency domain information. Furthermore, SpaBlock supplements spatial domain information in the frequency branch. Extensive experiments demonstrate that the proposed approach yields promising results in terms of both quantitative and qualitative metrics across various publicly available datasets.