A structure and texture revealing retinex model for low-light image enhancement

Low-light image enhancement is a crucial yet challenging task in computer vision and multimedia applications. Retinex-based approaches have been continuously explored in this domain. However, the Retinex decomposition is an ill-posed problem, as the proper constraints of illumination and reflectance should be considered to regularize the solution space. Aiming at a faithful enhancement, we develop a Structure and Texture Revealing Retinex (STR 2 ) model to accurately estimate the illumination and reflectance components. The proposed STR 2 model utilizes an exponential relative total variation method to draw structure and texture maps by analyzing the difference in gradient distribution between the illumination and reflectance components. The resulting structure and texture maps are used to regularize the illumination and reflectance components. With a tailored alternating optimization algorithm, the STR 2 model can jointly update the illumination and reflectance efficiently to produce a faithful enhanced image. Experimental results on several public datasets verify the effectiveness of the proposed model in low-light image enhancement.