DMCA
Image Completion Using Efficient Belief Propagation via Priority Scheduling and Dynamic Pruning
| Citations: | 61 - 0 self |
BibTeX
@MISC{Komodakis_imagecompletion,
author = {Nikos Komodakis and Georgios Tziritas},
title = {Image Completion Using Efficient Belief Propagation via Priority Scheduling and Dynamic Pruning},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
In this paper, a new exemplar-based framework is presented, which treats image completion, texture synthesis and image inpainting in a unified manner. In order to be able to avoid the occurrence of visually inconsistent results, we pose all of the above image-editing tasks in the form of a discrete global optimization problem. The objective function of this problem is always well-defined, and corresponds to the energy of a discrete Markov Random Field (MRF). For efficiently optimizing this MRF, a novel opti-mization scheme, called Priority-BP, is then proposed, which carries two very important extensions over the standard Belief Propagation (BP) algorithm: “priority-based message scheduling ” and “dynamic label pruning”. These two extensions work in cooperation to deal with the intolerable computational cost of BP, which is caused by the huge number of labels associated with our MRF. Moreover, both of our extensions are generic, since they do not rely on the use of domain-specific prior knowledge. They can therefore be applied to any MRF, i.e to a very wide class of problems in image processing and computer vision, thus managing to resolve what is currently considered as one major limitation of the Belief Propagation algorithm: its inefficiency in handling MRFs with very large discrete state-spaces. Experimental results on a wide variety of input images are presented, which demonstrate the effectiveness of our image-completion framework for tasks such as object removal, texture synthesis, text removal and image inpainting.
Keyphrases
priority scheduling dynamic pruning image inpainting texture synthesis inconsistent result domain-specific prior knowledge standard belief propagation image-editing task image completion major limitation dynamic label pruning image processing objective function priority-based message scheduling large discrete state-spaces computer vision wide class input image intolerable computational cost discrete global optimization problem unified manner discrete markov random field important extension huge number text removal belief propagation algorithm novel opti-mization scheme new exemplar-based framework wide variety object removal image-completion framework experimental result
