Next Article in Journal
Ultra-Dense Uplink UAV Lossy Communications: Trajectory Optimization Based on Mean Field Game
Previous Article in Journal
Adaptive Recombination-Based Control Strategy for Cell Balancing in Lithium-Ion Battery Packs: Modeling and Simulation
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

FreqSpatNet: Frequency and Spatial Dual-Domain Collaborative Learning for Low-Light Image Enhancement

1
School of Information Science and Engineering, Shenyang Ligong University, Shenyang 110159, China
2
Science and Technology Development Corporation, Shenyang Ligong University, Shenyang 110159, China
3
State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
4
University of Chinese Academy of Sciences, Beijing 100049, China
*
Author to whom correspondence should be addressed.
Electronics 2025, 14(11), 2220; https://doi.org/10.3390/electronics14112220
Submission received: 14 April 2025 / Revised: 26 May 2025 / Accepted: 27 May 2025 / Published: 29 May 2025

Abstract

Low-light images often contain noise due to the conditions under which they are taken. Fourier transform can reduce this noise in frequency while preserving the image detail embedded in the low-frequency components. Existing low-light image-enhancement methods based on CNN frameworks often fail to extract global feature information and introduce excessive noise, resulting in detail loss. To solve the above problems, we propose a low-light image-enhancement framework and achieve detail restoration and denoising by using Fourier transform. In addition, we design a dual-domain enhancement strategy, which cooperatively utilizes global frequency-domain feature extraction to improve the overall brightness of the image and the amplitude modulation of the spatial-domain convolution operation to perform local detail refinement to improve the quality of the image by suppressing noise, enhancing the contrast, and preserving the texture at the same time. Extensive experiments on low-light datasets show that our results outperform mainstream methods, especially in maintaining natural color distributions and recovering fine-grained details under extreme lighting conditions. We adopted two evaluation indicators, PSNR and SSIM. Our method improved the PSNR by 4.37% compared to the Restormer method and by 1.76% compared to the DRBN method.
Keywords: low-light image enhancement; Fourier transform; dual-domain enhancement; frequency domain low-light image enhancement; Fourier transform; dual-domain enhancement; frequency domain

Share and Cite

MDPI and ACS Style

Guan, Y.; Liu, M.; Chen, X.; Wang, X.; Luan, X. FreqSpatNet: Frequency and Spatial Dual-Domain Collaborative Learning for Low-Light Image Enhancement. Electronics 2025, 14, 2220. https://doi.org/10.3390/electronics14112220

AMA Style

Guan Y, Liu M, Chen X, Wang X, Luan X. FreqSpatNet: Frequency and Spatial Dual-Domain Collaborative Learning for Low-Light Image Enhancement. Electronics. 2025; 14(11):2220. https://doi.org/10.3390/electronics14112220

Chicago/Turabian Style

Guan, Yu, Mingsi Liu, Xi’ai Chen, Xudong Wang, and Xin Luan. 2025. "FreqSpatNet: Frequency and Spatial Dual-Domain Collaborative Learning for Low-Light Image Enhancement" Electronics 14, no. 11: 2220. https://doi.org/10.3390/electronics14112220

APA Style

Guan, Y., Liu, M., Chen, X., Wang, X., & Luan, X. (2025). FreqSpatNet: Frequency and Spatial Dual-Domain Collaborative Learning for Low-Light Image Enhancement. Electronics, 14(11), 2220. https://doi.org/10.3390/electronics14112220

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop