A Retinex-Based Variational Model with A Nonlocal Gradient-Type Constraint for Low-Light Image Enhancement

Images captured under low-light conditions pose significant limitations in many applications. Removing the illumination effects and enhancing the quality of such images is crucial. In this paper, we introduce a low-light image enhancement variational method based on the Retinex decomposition into illumination, reflectance, and noise. Our model integrates a novel nonlocal gradient-type fidelity term designed to preserve structural details. Additionally, we propose an automatic gamma correction module. Since the noise is explicitly addressed, no post-processing is required for denoising. Experimental results show that our method compares favorably with state-of-the-art deep learning-based approaches.