Retinex-Based Low-Light Image Enhancement via Spatial-Channel Redundancy Compression and Joint Attention
Electronics · 29.05.2025 · 14 (11) · 2212
DOI: 10.3390/electronics14112212 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 29.05.2025. Verfasst von Jinlong Chen und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangxi Key R&D Plan Project.
Abstract (Originalsprache)
Low-light image enhancement (LLIE) methods based on Retinex theory often involve complex, multi-stage training and are commonly built on convolutional neural networks (CNNs). However, CNNs suffer from limitations in capturing long-range dependencies and often introduce redundant computations, leading to high computational costs. To address these issues, we propose a lightweight and efficient LLIE framework that incorporates an optimized CNN compression strategy and a novel attention mechanism. Specifically, we design a Spatial-Channel Feature Reconstruction Module (SCFRM) to suppress spatial and channel redundancy via split-reconstruction and separation-fusion strategies. SCFRM is composed of two parts, a Spatial Feature Enhancement Unit (SFEU) and a Channel Refinement Block (CRB), which together enhance feature representation while reducing computational load. Additionally, we introduce a Joint Attention (JOA) mechanism that captures long-range dependencies across spatial dimensions while preserving positional accuracy. Our Retinex-based framework separates the processing of illumination and reflectance components using a Denoising Network (DNNet) and a Light Enhancement Network (LINet). SCFRM is embedded into DNNet for improved denoising, while JOA is applied in LINet for precise brightness adjustment. Extensive experiments on multiple benchmark datasets demonstrate that our method achieves superior or comparable performance to state-of-the-art LLIE approaches, while significantly reducing computational complexity. On the LOL and VE-LOL datasets, our approach achieves the best or second-best scores in terms of PSNR and SSIM metrics, validating its effectiveness and efficiency.
Förderung
- Guangxi Key R&D Plan Project
Zitieren
APA
Chen, J., Xiao, Z., Qin, X., & Luo, D. (2025). Retinex-Based Low-Light Image Enhancement via Spatial-Channel Redundancy Compression and Joint Attention. Electronics, 14(11), 2212. https://doi.org/10.3390/electronics14112212
Vancouver
Chen J, Xiao Z, Qin X, Luo D. Retinex-Based Low-Light Image Enhancement via Spatial-Channel Redundancy Compression and Joint Attention. Electronics. 2025;14(11):2212. doi:10.3390/electronics14112212
BibTeX
@article{Chen2025,
author = {Chen, Jinlong and Xiao, Zhigang and Qin, Xingguo and Luo, Deming},
title = {Retinex-Based Low-Light Image Enhancement via Spatial-Channel Redundancy Compression and Joint Attention},
journal = {Electronics},
year = {2025},
volume = {14},
number = {11},
pages = {2212},
doi = {10.3390/electronics14112212}
}
EUVIMED