Single image super-resolution via blind blurring estimation and dictionary learning

Abstract

Learning-based methods have been becoming the mainstream of single image super resolution (SR) technologies. This kind of methods makes it effective to generate a high resolution (HR) image from a single low resolution (LR) image. There exists, however, two main problems with these methods: the quality of training data and the computational demand. We propose a novel framework for single image SR tasks in this paper, which consists of blur kernel estimation (BKE) and dictionary learning. BKE is utilized for improving the quality of training samples and realized by minimizing the dissimilarity between cross-scale patches iteratively. Couple dictionaries are trained by improved training samples before sparse recovery. More important is that a selective patch processing (SPP) strategy is adopted in BKE and sparse recovery, which brings more accurate BKE results and immensely reduces time consumption of the entire process. The experiments show that the proposed method produces more precise BKE estimation and better SR recovery than several typical SR algorithms at a higher efficiency.