Deblurring is an inverse problem which has traditionally been studied from a signal processing perspective. In this paper we consider the role of extra information in the form of prior knowledge of the object class to solve this problem. Specifically, we incorporate unlabeled image data of the object class, say natural images, in the form of a patch-manifold prior for the object class. The manifold is implicitly estimated from the given unlabeled data. We show how the patch manifold prior effectively exploits the availability of the sample class data for regularizing the deblurring problem.
© 2010 Optical Society of AmericaPDF Article
More Like This
DMC1 Digital Image Processing and Analysis (DIPA) 2010
Robert Muise and David Bottisti
CM1C.2 Computational Optical Sensing and Imaging (COSI) 2013
Roberto Baena Gallé, Szymon Gladysz, Laurent Mugnier, Rao Gudimetla, Robert L. Johnson, and Lee Kann
SM1F.3 Signal Recovery and Synthesis (SRS) 2014