Multi-path parallel enhancement of low-light images based on multiscale spatially aware Retinex decomposition

Abstract

To resolve the issues of color distortion and detail blurring, this study proposes a multi-path parallel enhancement of low-light images (LLIs) based on multiscale spatially aware Retinex decomposition (MUSRetinex-Net). MUSRetinex-Net consists of three subnetworks. Firstly, MUSRetinex-Net inputs LLIs into an illumination level estimation image guided multiscale spatial perception decomposition network (MSPD-Net) which completes Retinex decomposition to retain richer color information and detail structure; then reflectance maps from LLIs are inputted into a three-pass parallel reflectance maps recovery network (TPR-Net) for more desirable noise removal and color recovery; illumination maps from LLIs are inputted into a multi-branch attention illumination maps adjustment network (MAA-Net) for adjustment to obtain a more accurate estimation of illumination levels. In this study, six publicly accessible datasets are utilized for experiments, two referenced evaluation metrics, and four non-referenced evaluation metrics are utilized for assessment and analysis. The experimental results show that the low-light image enhancement (LLIE) effects obtained by this study method are more consistent with the recognition level of the human eye and the structure of the natural environment. The method achieves the optimal referenced evaluation metrics score and the most comprehensive non-referenced evaluation metrics score on all six public datasets, with extremely high enhancement performance and generalization ability.