Super-resolution through neighbor embedding

In this paper, we propose a novel method for solving single-image super-resolution problems. Given a low-resolution image as input, we recover its high-resolution counterpart using a set of training examples. While this formulation resembles other learning-based methods for super-resolution, our method has been inspired by recent manifold teaming methods, particularly locally linear embedding (LLE). Specifically, small image patches in the lowand high-resolution images form manifolds with similar local geometry in two distinct feature spaces. As in LLE, local geometry is characterized by how a feature vector corresponding to a patch can be reconstructed by its neighbors in the feature space. Besides using the training image pairs to estimate the high-resolution embedding, we also enforce local compatibility and smoothness constraints between patches in the target high-resolution image through overlapping. Experiments show that our method is very flexible and gives good empirical results.

1. Introduction

Super-resolution is the problem of generating a high-resolution image from one or more low-resolution images. While most methods have been proposed for super-resolution based on multiple low-resolution images of the same scene (e.g., [2], [6], [8], [2] [2]), the focus of this paper is on generating a high-resolution image from a single low-resolution image, with the help of a set of one or more training images from scenes of the same or different types. We refer to this as the single-image super-resolution problem.