We will demonstrate the effectiveness of sparsity as a prior for regularizing the otherwise ill-posed super-resolution problem. The principle of compressed sensing ensures that under mild conditions, the sparse representation can be correctly recovered from the downsampled signal. 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. We approach this problem from the perspective of compressed sensing. N2 - This paper addresses the problem of generating a super-resolution (SR) image from a single low-resolution input image. T1 - Image super-resolution as sparse representation of raw image patches 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.", 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.Ībstract = "This paper addresses the problem of generating a super-resolution (SR) image from a single low-resolution input image. This paper addresses the problem of generating a super-resolution (SR) image from a single low-resolution input image.