An Adaptively Edge-guided Back-projection Algorithm for Single Image Super-resolution

Abstract

The iterative back-projection (IBP) algorithm for single image super-resolution (SR) can not guarantee the edge smoothness because the reconstruction error is back-projected isotropically. Furthermore, in the case that there is only one low-resolution input, the estimation of the reconstruction error is easily affected by noise. Thus, this algorithm is highly sensitive to noise. The focus of this paper is to overcome the two disadvantages. Firstly, we present a novel IBP algorithm which incorporates an adaptively edge-guided interpolation into the back-projection process. Thus, the back-projection process can be guided by the local edge information adaptively. Experimental results show that the proposed algorithm outperforms the state-of-the-art IBP methods. It can generate a highresolution image with smooth edges. Secondly, we propose a robust IBP algorithm which exploits nonlocal redundancies to improve the reliability of the reconstruction error estimation. Experimental results show the proposed algorithm can work well for the noisy images.