DMCA
Image superresolution as sparse representation of raw image patches (2008)
Cached
Download Links
| Citations: | 135 - 19 self |
BibTeX
@MISC{Yang08imagesuperresolution,
author = {Jianchao Yang and John Wright and Yi Ma and Thomas Huang},
title = {Image superresolution as sparse representation of raw image patches },
year = {2008}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
This paper addresses the problem of generating a superresolution (SR) image from a single low-resolution input image. We approach this problem from the perspective of compressed sensing. The low-resolution image is viewed as downsampled version of a high-resolution image, whose patches are assumed to have a sparse representation with respect to an over-complete dictionary of prototype signalatoms. The principle of compressed sensing ensures that under mild conditions, the sparse representation can be correctly recovered from the downsampled signal. We will demonstrate the effectiveness of sparsity as a prior for regularizing the otherwise ill-posed super-resolution problem. We further show that a small set of randomly chosen raw patches from training images of similar statistical nature to the input image generally serve as a good dictionary, in the sense that the computed representation is sparse and the recovered high-resolution image is competitive or even superior in quality to images produced by other SR methods.
Keyphrases
sparse representation image superresolution raw image patch compressed sensing mild condition good dictionary high-resolution image single low-resolution input image input image prototype signalatoms small set computed representation recovered high-resolution image raw patch downsampled signal over-complete dictionary downsampled version ill-posed super-resolution problem sr method low-resolution image similar statistical nature
