Image De-Raining Via Rdl: When Reweighted Convolutional Sparse Coding Meets Deep Learning

Over the past few decades, image de-raining has witnessed substantial progress due to the development of priors and deep learning based methods. However, few studies combine the merits of both. In this paper, we argue that domain expertise of conventional convolutional sparse coding (CSC) is still valuable, and it can be combined with the key ingredients of deep learning to achieve further improved results. Specifically, motivated by the success of reweighting algorithms, we propose solving the CSC model by learning weighted iterative soft thresholding algorithm (LwISTA) in a convolutional manner where the reweighted l(1)-norm is introduced. Based on this, we present a novel framework for single image de-raining, in which the channel attention is employed to learn the weight. Extensive experiments demonstrate the superiority of our method over recent state-of-the-art image de-raining methods, in terms of both quantitative and qualitative results.