SID-NISM: A Self-supervised Low-light Image Enhancement Framework
This work addresses the problem of low visibility in low-light images, which degrades visual aesthetics and the performance of computer vision algorithms, offering an incremental improvement for image processing practitioners.
This paper proposes SID-NISM, a self-supervised framework for enhancing low-light images. It decomposes images into reflectance, illumination, and noise, then enhances the illumination map, resulting in more natural images with fewer artifacts on public datasets.
When capturing images in low-light conditions, the images often suffer from low visibility, which not only degrades the visual aesthetics of images, but also significantly degenerates the performance of many computer vision algorithms. In this paper, we propose a self-supervised low-light image enhancement framework (SID-NISM), which consists of two components, a Self-supervised Image Decomposition Network (SID-Net) and a Nonlinear Illumination Saturation Mapping function (NISM). As a self-supervised network, SID-Net could decompose the given low-light image into its reflectance, illumination and noise directly without any prior training or reference image, which distinguishes it from existing supervised-learning methods greatly. Then, the decomposed illumination map will be enhanced by NISM. Having the restored illumination map, the enhancement can be achieved accordingly. Experiments on several public challenging low-light image datasets reveal that the images enhanced by SID-NISM are more natural and have less unexpected artifacts.