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. It is effective to generate a high- resolution image from a single low resolution input. However, the quality of training data and the computational demand are two main problems. We propose a novel process framework for single image SR tasks aiming at these two problems, which consists of blur kernel estimation (BKE) and dictionary learning. BKE is utilized for improving the quality of training samples and compatibility between training samples and test samples, which is realized by minimizing the dissimilarity between cross-scale patches iteratively (intuitively be equivalent to maximizing the similarity of cross-scale patches). A selective patch processing (SPP) strategy is adopted in BKE and sparse recovery to re- duce the number of patches needed to be processed. The fact that nature images usually contain continuity and discontinuity simultaneously ensures the feasibility of SPP. The experimental results show that our method produces more precise estimation for blurring kernel and better SR effect than several state-of-the- art SR algorithms on equal conditions, but needs much less computation time.