Example-Driven Manifold Priors for Image Deconvolution

TitleExample-Driven Manifold Priors for Image Deconvolution
Publication TypeJournal Articles
Year of Publication2011
AuthorsNi J, Turaga P, Patel VM, Chellappa R
JournalImage Processing, IEEE Transactions on
Pagination3086 - 3096
Date Published2011/11//
ISBN Number1057-7149
KeywordsBayesian, cross-validation, data;Bayes, deconvolution;image, determination;deblurring, estimation;, framework;GCV, function;automatic, function;image, image, image;patch-manifold, manifold, method;iteration, method;natural, methods;deconvolution;image, methods;natural, parameter, prior;generalized, prior;unlabeled, problem, regularization, regularization;example-driven, restoration, restoration;iterative, scenes;parameter

Image restoration methods that exploit prior information about images to be estimated have been extensively studied, typically using the Bayesian framework. In this paper, we consider the role of prior knowledge of the object class in the form of a patch manifold to address the deconvolution 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 prior is implicitly estimated from the given unlabeled data. We show how the patch-manifold prior effectively exploits the available sample class data for regularizing the deblurring problem. Furthermore, we derive a generalized cross-validation (GCV) function to automatically determine the regularization parameter at each iteration without explicitly knowing the noise variance. Extensive experiments show that this method performs better than many competitive image deconvolution methods.