Clean Retinex Decomposition Network for Low-Light Image Enhancement

Images captured in low-light environments will bring about various complex degradations. The main task of low-light image enhancement (LLIE) is to improve the brightness and restore the details of the image, thereby producing images that are more in line with human perception. Retinex-based methods decompose images into illumination and reflectance components, and enhance images by adjusting illumination and restoring reflectance details. However, the presence of noise in images usually leads to inaccurate decomposition, resulting in results that deviate from reality. In order to prevent the influence of noise on the subsequent decomposition tasks, we first denoise the low-light images, perform Retinex decomposition on the denoised images, and try to pair the low-light images to maintain the consistency of the reflectance components. Specifically, we propose a Clean Decomposition Network(CDNet), an unsupervised learning method that first performs denoising on low-light image pairs to prevent loss of details and color deviation, and then performs Retinex decomposition, and guides network optimization through a carefully designed denoising network and loss function. Extensive experiments on six public datasets including LOL and SICE show that our method achieves better enhancement performance compared with the most advanced unsupervised methods and is also competitive with supervised methods.