Attention-based Broad Self-guided Network for Low-light Image Enhancement

Low-light image enhancement is widely used in many fields, such as target detection, face recognition, and image segmentation. In recent years, Deep Learning methods have achieved impressive breakthroughs in low-light image enhancement. However, most of them mine high-dimensional features of images by stacking network structures and deepening the depth of the network, which causes more runtime costs for single image enhancement. To reduce inference time while fully extracting local features and global features of low-light images, we propose an Attention-based Broad Self-guided Network for real-world low-light image Enhancement. Compared to U-net structure [1], such a self-guided structure requires a smaller number of parameters and enables us to achieve better effectiveness. To extract local information more efficiently, we designed a Multilevel Guided Densely Connected Attention block, which can be considered as a novel extension of the densely connected blocks in feature space. In addition, we also offer a more efficient module to extract global information from images, which is called the Global Spatial Attention module. The proposed network is validated by lots of mainstream benchmarks. Many experimental results show that the proposed network outperforms most state-of-the-art low-light image Enhancement methods. Our code is available at https://github.com/paullenwyue/ABSGNet.