Enhancing Low-Light Color Image via L0 Regularization and Reweighted Group Sparsity

Abstract

Classic Retinex model based low-light image enhancement methods ignored the interference of noise, which causes annoying artifacts. In this paper, we propose to estimate the illumination, reflectance and suppress the noise in a whole framework. Instead of using the <inline-formula> <tex-math notation= LaTeX >$L_{1}$ </tex-math></inline-formula> norm to constrain the piece-wise smoothness, we utilize the <inline-formula> <tex-math notation= LaTeX >$L_{0}$ </tex-math></inline-formula> norm to preserve the structure of the illumination map and remove the intensive noise. The clean reflectance is obtained via a novel group sparsity regularization to preserve the small scale details. Instead of using a zero-mean model for all sparse coefficients, we propose to adaptively estimate the mean of each coefficient according to the statistical characteristics of the image content. A re-weighting scheme is introduced to adjust how close the estimated patch is to the mean value. In addition, based on the observation that the noise levels in different color channels are different, the noise variance in each channel is estimated and updated during the model optimization process. Experimental results show that the proposed method outperforms the compared schemes in terms of both objective quality and visual quality.