Single Image Super-Resolution Using Sparse Representation
April 14th, 2010
SIAM Imaging Science 2010 Conference, Chicago. Mini-Symp. on Recent Advances in Sparse and Non-local Image Regularization (organized by Gabriel Peyre, Peyman Milanfar, and Michael Elad).

Scaling up a single image while preserving is sharpness and visual-quality is a difficult and highly ill-posed inverse problem. A series of algorithms have been proposed over the years for its solution, with varying degrees of success. In CVPR 2008, Yang, Wright, Huang and Ma proposed a solution to this problem based on sparse representation modeling and dictionary learning. In this talk I present a variant of their method with several important differences. In particular, the proposed algorithm does not need a separate training phase, as the dictionaries are learned directly from the image to be scaled-up. Furthermore, the high-resolution dictionary is learned differently, by forcing its alignment with the low-resolution one. We show the benefit these modifications bring in terms of simplicity of the overall algorithm, and its output quality.

This is a joint work with Roman Zeyde and Matan Protter (CS - Technion).