Image super-resolution as sparse representation of raw image patches

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 im...

• Type: Conference
• Year: 2008
• Where: CVPR
• Authors: Jianchao Yang, John Wright, Thomas S. Huang, Yi Ma
• Keywords: Computed Representation, Computer Vision, CVPR 2008, Ill-posed Super-resolution Problem, Low-resolution Image, Low-resolution Input Image, Sparse Representation