Single Image Super-Resolution using Gaussian Mixture Model

In this paper we present a novel method for single image super-resolution (SR). Given an input low-resolution image, we create a pyramid pair: the ground truth pyramid and the interpolated pyramid. This method aims to model the relationship between pixel value in ground truth pyramid and its corresponding 8-neighborhood vector in interpolated pyramid using Gaussian Mixture Model (GMM). Each pixel in final high-resolution image is predicted by its corresponding 8-neighborhood vector through the trained GMM. Unlike the previous example-based SR method, our algorithm only utilizes the information of input image rather than the external image database. Our proposed algorithm achieves much better results than the state of the art algorithms in terms of both objective measurement and visual perception.