A MODEL LEARNING APPROACH FOR LOW LIGHT IMAGE RESTORATION

We study the problem of low light image restoration through contrast enhancement and denoising. We approach this problem by learning a model that relates a noisy low light and well lit image pair. The low light image is modeled to suffer from contrast distortion and additive noise. In particular, we model the loss of contrast through a global parametric function, which enables the estimation of the underlying noise. We then use a pair of convolutional neural network (CNN) models to learn the noise and the parameters of a function to achieve contrast enhancement. This contrast enhancement function is modeled as a linear combination of multiple gamma enhancers. We show through extensive evaluations that our Low Light Image Model for Enhancement Network (LLIMENet) achieves superior restoration performance when compared to other methods on several publicly available datasets.