Show simple item record

dc.contributor.authorMärz, Thomas
dc.date.accessioned2016-02-25T13:32:06Z
dc.date.available2016-02-25T13:32:06Z
dc.date.issued2011-01
dc.identifier.citationMärz T (2011) Image Inpainting Based on Coherence Transport with Adapted Distance Functions. SIAM Journal on Imaging Sciences 4: 981–1000. Available: http://dx.doi.org/10.1137/100807296.
dc.identifier.issn1936-4954
dc.identifier.doi10.1137/100807296
dc.identifier.urihttp://hdl.handle.net/10754/598556
dc.description.abstractWe discuss an extension of our method image inpainting based on coherence transport. For the latter method the pixels of the inpainting domain have to be serialized into an ordered list. Until now, to induce the serialization we have used the distance to boundary map. But there are inpainting problems where the distance to boundary serialization causes unsatisfactory inpainting results. In the present work we demonstrate cases where we can resolve the difficulties by employing other distance functions which better suit the problem at hand. © 2011 Society for Industrial and Applied Mathematics.
dc.description.sponsorshipReceived by the editors September 1, 2010; accepted for publication (in revised form) July 26, 2011; published electronically October 20, 2011. This work was supported in part by the Graduiertenkolleg Angewandte Algorithmische Mathematik (GKAAM) funded by the Deutsche Forschungsgemeinschaft (DFG) at the Technische Universitat Munchen (TUM), and by award KUK-C1-013-04 made by King Abdullah University of Science and Technology (KAUST).
dc.publisherSociety for Industrial & Applied Mathematics (SIAM)
dc.subjectDistance functions
dc.subjectImage inpainting
dc.subjectImage processing
dc.titleImage Inpainting Based on Coherence Transport with Adapted Distance Functions
dc.typeArticle
dc.identifier.journalSIAM Journal on Imaging Sciences
dc.contributor.institutionUniversity of Oxford, Oxford, United Kingdom
kaust.grant.numberKUK-C1-013-04


This item appears in the following Collection(s)

Show simple item record