A new two-stage low-light enhancement network with progressive attention fusion strategy

• Published in: Signal processing. Image communication Vol. 130; p. 117229
• Main Authors: Zhu, Hegui, Wang, Luyang, Gao, Zhan, Liu, Yuelin, Zhao, Qian
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.01.2025
• Subjects: Attention mechanism; Global feature fusion; Local detail restoration; Low-light image enhancement; Progressive attention fusion; Attention mechanism; Local detail restoration; Progressive attention fusion; Global feature fusion; Low-light image enhancement
• DOI: 10.1016/j.image.2024.117229
• ISSN: 0923-5965

Low-light image enhancement is a very challenging subject in the field of computer vision such as visual surveillance, driving behavior analysis, and medical imaging . It has a large number of degradation problems such as accumulated noise, artifacts, and color distortion. Therefore, how to solve the degradation problems and obtain clear images with high visual quality has become an important issue. It can effectively improve the performance of high-level computer vision tasks. In this study, we propose a new two-stage low-light enhancement network with a progressive attention fusion strategy, and the two hallmarks of this method are the use of global feature fusion (GFF) and local detail restoration (LDR), which can enrich the global content of the image and restore local details. Experimental results on the LOL dataset show that the proposed model can achieve good enhancement effects. Moreover, on the benchmark dataset without reference images, the proposed model also obtains a better NIQE score, which outperforms most existing state-of-the-art methods in both quantitative and qualitative evaluations. All these verify the effectiveness and superiority of the proposed method. •Propose a two-stage low-light enhancement network with a progressive attention fusion strategy.•Design a global feature fusion block (GFF) to fuse features from different scales.•Propose a local detail restoration block (LDR), which can effectively reduce noise.