Fast image super-resolution based on in-place example regression

We propose a fast regression model for practical sin-gle image super-resolution based on in-place examples, by leveraging two fundamental super-resolution approaches— learning from an external database and learning from self-examples. Our in-place self-similarity refines the recently proposed local self-similarity by proving that a patch in the upper scale image have good matches around its origin lo-cation in the lower scale image. Based on the in-place ex-amples, a first-order approximation of the nonlinear map-ping function from low- to high-resolution image patches is learned. Extensive experiments on benchmark and real-world images demonstrate that our algorithm can produce natural-looking results with sharp edges and preserved fine details, while the current state-of-the-art algorithms are prone to visual artifacts. Furthermore, our model can eas-ily extend to deal with noise by combining the regression results on multiple in-place examples for robust estimation. The algorithm runs fast and is particularly useful for prac-tical applications, where the input images typically contain diverse textures and they are potentially contaminated by noise or compression artifacts. 1