Super-resolution from a single image

TLDR

Super‑resolution methods are generally divided into classical multi‑image techniques that combine subpixel‑shifted images and example‑based approaches that learn patch correspondences from a database. This paper proposes a unified framework that merges these two families and demonstrates its application to single‑image super‑resolution without external examples. The framework exploits the redundancy of image patches both within the same scale (subpixel misalignments) and across scales, selecting for each pixel the best resolution enhancement based on this intra‑ and inter‑scale recurrence. The method successfully produces high‑resolution images from a single input, achieving super‑resolution without a database or prior examples.

Abstract

Methods for super-resolution can be broadly classified into two families of methods: (i) The classical multi-image super-resolution (combining images obtained at subpixel misalignments), and (ii) Example-Based super-resolution (learning correspondence between low and high resolution image patches from a database). In this paper we propose a unified framework for combining these two families of methods. We further show how this combined approach can be applied to obtain super resolution from as little as a single image (with no database or prior examples). Our approach is based on the observation that patches in a natural image tend to redundantly recur many times inside the image, both within the same scale, as well as across different scales. Recurrence of patches within the same image scale (at subpixel misalignments) gives rise to the classical super-resolution, whereas recurrence of patches across different scales of the same image gives rise to example-based super-resolution. Our approach attempts to recover at each pixel its best possible resolution increase based on its patch redundancy within and across scales.