Single image super-resolution based on self-examples using context-dependent subpatches

Self-example-based super-resolution (SR) methods utilize internal dictionaries to reconstruct a high-resolution (HR) image from a single low-resolution (LR) input image. In general, a square-sized patch is used to find the LR-HR correspondences in the dictionaries. However, this may be a difficult issue because the LR input image and the dictionaries are of different scales. Inspired by this observation, we propose a novel self-example-based SR method, using context-dependent multi-shaped subpatches. Each LR input patch is segmented into multiple subpatches according to the context of the patch, enabling us to extract the better LR-HR correspondences. Our experimental results show that the proposed subpatch-based SR generates competitive high-quality HR images compared to state-of-the-art methods, with visually sharper edges that result in better visual quality.

1. Introduction

Currently, super-resolution (SR) is a very active area of research because it can overcome the limitations of low resolution (LR) image sensors. SR aims to generate a high-resolution (HR) image from an LR image, by carefully estimating the missing high-frequency information. HR image reconstruction using SR, however, is known to be an ill-posed inverse problem because there exist multiple HR images that can be recovered from a single LR image, implying that a unique solution does not exist. To overcome this problem, many effective SR methods have been suggested.