A low-light image enhancement model based on anisotropic weighted exponential local derivatives

Low-light images incur several complicated degradations such as low brightness, poor contrast, and higher noise. Retinex theory, which decomposes a low-light image into illumination and reflection components based on local image derivatives, is widely used in the field of shimmering image enhancement. In this paper, we propose a new low-light image enhancement model based on the Retinex theory to reduce the above distortions. To be more specific, we first introduce a new structural texture extractor (NSTE) based on the local image derivatives properties to generate the texture and structure maps of the observed images. Compared to existing structural texture extractors, NSTE has two key designs: anisotropic weighting and adaptive exponential term. The aim is to generate structural maps with clear edge and texture maps with salient details. Subsequently, these two images are used to regularize the illumination and reflection components of the variational decomposition model, respectively. Finally, we developed a luminance correction function and a detail enhancement function to enhance the illumination and reflectance, respectively. This aims to improve the viewing experience, mitigate over-enhancement, and minimize detail distortion. We choose the alternating direction method of multipliers (ADMM) to solve the optimization model. Experimental results on several low-light datasets demonstrate that our proposed method can achieve better quantitative and qualitative performance than state-of-the-art methods.