Low-Light Image Enhancement Network Based on Multi-Scale Residual Feature Integration

Owing to insufficient light, images captured in low-light environment have a series of image degradation problems such as low visibility, color deviation, and noise. To address these problems, an image enhancement network based on multi-scale residual feature integration (IEN-MRFI) is proposed, which includes two modules: a shallow feature extraction module (SFEM) and a multi-scale feature integration module (MFIM). First, the SFEM is constructed for extracting multi-scale shallow features through three-scale convolutional layers and smooth convolution residual blocks (SCRBs). The constructed SCRB runs through the entire network to extract features and avoid gridding artifacts. Then, the MFIM is constructed by cascading multiple feature integration residual blocks to fuse the shallow and deep features of the same scale. Finally, the fused features are passed through a convolutional layer to obtain an enhanced result. In addition, to improve the generalization ability of our network, this study constructs an outdoor dataset for the training of the low-light image enhancement network. Experiments on indoor and outdoor images show that the enhancement results of our method can provide more accurate color saturation and richer details than those of some state-of-the-art methods. We intend to make the constructed dataset public after our paper is accepted for publication.