Image Super-Resolution as Sparse Representation of Raw Image Patches. Yang, J., Wright, J., Huang, T., & Ma, Y. In 2008 IEEE Conference on Computer Vision and Pattern Recognition, pages 1–8, June, 2008. ISSN: 1063-6919doi abstract bibtex This paper addresses the problem of generating a super-resolution (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 signal-atoms. 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.
@inproceedings{yang_image_2008,
title = {Image {Super}-{Resolution} as {Sparse} {Representation} of {Raw} {Image} {Patches}},
doi = {10.1109/CVPR.2008.4587647},
abstract = {This paper addresses the problem of generating a super-resolution (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 signal-atoms. 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.},
language = {en},
booktitle = {2008 {IEEE} {Conference} on {Computer} {Vision} and {Pattern} {Recognition}},
author = {Yang, Jianchao and Wright, John and Huang, Thomas and Ma, Yi},
month = jun,
year = {2008},
note = {ISSN: 1063-6919},
keywords = {\#CVPR{\textgreater}08, \#Representation{\textgreater}SR, \#Sparse, /readed, Compressed sensing, Dictionaries, Equations, Image reconstruction, Image resolution, Inverse problems, Markov random fields, Prototypes, Signal resolution, Strontium, ⭐⭐⭐⭐⭐, 🚩},
pages = {1--8},
}
Downloads: 0
{"_id":"5HGqMv4KhJT9vknos","bibbaseid":"yang-wright-huang-ma-imagesuperresolutionassparserepresentationofrawimagepatches-2008","downloads":0,"creationDate":"2018-01-22T16:01:06.206Z","title":"Image Super-Resolution as Sparse Representation of Raw Image Patches","author_short":["Yang, J.","Wright, J.","Huang, T.","Ma, Y."],"year":2008,"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/zzhenry2012","bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Image Super-Resolution as Sparse Representation of Raw Image Patches","doi":"10.1109/CVPR.2008.4587647","abstract":"This paper addresses the problem of generating a super-resolution (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 signal-atoms. 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.","language":"en","booktitle":"2008 IEEE Conference on Computer Vision and Pattern Recognition","author":[{"propositions":[],"lastnames":["Yang"],"firstnames":["Jianchao"],"suffixes":[]},{"propositions":[],"lastnames":["Wright"],"firstnames":["John"],"suffixes":[]},{"propositions":[],"lastnames":["Huang"],"firstnames":["Thomas"],"suffixes":[]},{"propositions":[],"lastnames":["Ma"],"firstnames":["Yi"],"suffixes":[]}],"month":"June","year":"2008","note":"ISSN: 1063-6919","keywords":"#CVPR\\textgreater08, #Representation\\textgreaterSR, #Sparse, /readed, Compressed sensing, Dictionaries, Equations, Image reconstruction, Image resolution, Inverse problems, Markov random fields, Prototypes, Signal resolution, Strontium, ⭐⭐⭐⭐⭐, 🚩","pages":"1–8","bibtex":"@inproceedings{yang_image_2008,\n\ttitle = {Image {Super}-{Resolution} as {Sparse} {Representation} of {Raw} {Image} {Patches}},\n\tdoi = {10.1109/CVPR.2008.4587647},\n\tabstract = {This paper addresses the problem of generating a super-resolution (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 signal-atoms. 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.},\n\tlanguage = {en},\n\tbooktitle = {2008 {IEEE} {Conference} on {Computer} {Vision} and {Pattern} {Recognition}},\n\tauthor = {Yang, Jianchao and Wright, John and Huang, Thomas and Ma, Yi},\n\tmonth = jun,\n\tyear = {2008},\n\tnote = {ISSN: 1063-6919},\n\tkeywords = {\\#CVPR{\\textgreater}08, \\#Representation{\\textgreater}SR, \\#Sparse, /readed, Compressed sensing, Dictionaries, Equations, Image reconstruction, Image resolution, Inverse problems, Markov random fields, Prototypes, Signal resolution, Strontium, ⭐⭐⭐⭐⭐, 🚩},\n\tpages = {1--8},\n}\n\n\n\n","author_short":["Yang, J.","Wright, J.","Huang, T.","Ma, Y."],"key":"yang_image_2008","id":"yang_image_2008","bibbaseid":"yang-wright-huang-ma-imagesuperresolutionassparserepresentationofrawimagepatches-2008","role":"author","urls":{},"keyword":["#CVPR\\textgreater08","#Representation\\textgreaterSR","#Sparse","/readed","Compressed sensing","Dictionaries","Equations","Image reconstruction","Image resolution","Inverse problems","Markov random fields","Prototypes","Signal resolution","Strontium","⭐⭐⭐⭐⭐","🚩"],"metadata":{"authorlinks":{}},"downloads":0,"html":""},"search_terms":["image","super","resolution","sparse","representation","raw","image","patches","yang","wright","huang","ma"],"keywords":["#cvpr\\textgreater08","#representation\\textgreatersr","#sparse","/readed","compressed sensing","dictionaries","equations","image reconstruction","image resolution","inverse problems","markov random fields","prototypes","signal resolution","strontium","⭐⭐⭐⭐⭐","🚩"],"authorIDs":[],"dataSources":["9cexBw6hrwgyZphZZ","nZHrFJKyxKKDaWYM8"]}