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: 1063-6919
doi  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