A new method for image super-resolution with multi-channel constraints

Abstract

Most recent learning-based image super-resolution (SR) methods have attracted much interest. This paper proposes a new SR method with multi-channel constraints, which integrates clustering, collaborative representation, and progressive multi-layer mapping relationships to reconstruct high-resolution (HR) color image. In order to collect chrominance information, the training patches from RGB channels are clustered into different subspaces, and a number of neighbor subsets are grouped. Then the optimization problem with color channel constraints is solved by using the classical gradient technique. Finally, a continuous reconstructive structure, which learns multi-layer mapping relationships between intermediate output and corresponding original HR image, is designed to obtain the desired HR image. Extensive experiments on several commonly used image SR testing datasets indicate that the proposed method achieves state-of-the-art image SR results.