Low-Light Image Enhancement Based On Retinex and Saliency Theories

Abstract

Low-light images enhancement of real scenes is a challenge task, however, existing algorithms always encounter the problems of over-enhancement, noises amplification and low subjective evaluation. One reason of these problems lies in the missing of high-level vision information. Therefore, this paper present a novel low-light image enhancement framework based on retinex and saliency theories. We first adopts a deep neural network model i.e. Saliency Attentive Model to predict the saliency map of low-light image and detect its salient regions. Then, we utilize one retinex model based method to enhance the whole low-light image. Then we fuse the generated saliency map and the enhanced image together to acquire a well-enhanced image. Experiments verify the significance of our algorithm by comparing with general low-light image enhancement method without saliency.