Show simple item record

dc.contributor.authorTartavel, Guillaume
dc.contributor.authorPeyré, Gabriel
dc.contributor.authorGousseau, Yann
dc.date.accessioned2017-11-22T12:17:46Z
dc.date.available2017-11-22T12:17:46Z
dc.date.issued2016
dc.identifier.issn1936-4954
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/17015
dc.language.isoenen
dc.subjectSuper-resolution
dc.subjectTotal variation
dc.subjectDenoising
dc.subjectGeneralized Gaussian Distributions
dc.subjectOptimal transport
dc.subjectWasserstein
dc.subjectimpulse noise removal
dc.subject.ddc621.3en
dc.titleWasserstein Loss for Image Synthesis and Restoration
dc.typeArticle accepté pour publication ou publié
dc.description.abstractenThis paper presents a novel variational approach to impose statistical constraints to the output of both image generation (to perform typically texture synthesis) and image restoration (for instance to achieve denoising and super-resolution) methods. The empirical distributions of linear or non-linear descriptors are imposed to be close to some input distributions by minimizing a Wasserstein loss, i.e. the optimal transport distance between the distributions. We advocate the use of a Wasserstein distance because it is robust when using discrete distributions without the need to resort to kernel estimators. We showcase different estimators to tackle various image processing applications. These estimators include linear wavelet-based filtering to account for simple textures, non-linear sparse coding coefficients for more complicated patterns, and the image gradient to restore sharper contents. For applications to texture synthesis, the input distributions are the empirical distributions computed from an exemplar image. For image denoising and super-resolution, the estimation process is more difficult; we propose to make use of parametric models and we show results using Generalized Gaussian Distributions.
dc.relation.isversionofjnlnameSIAM Journal on Imaging Sciences
dc.relation.isversionofjnlvol9
dc.relation.isversionofjnlissue4
dc.relation.isversionofjnldate2016
dc.relation.isversionofjnlpages1726-1755
dc.relation.isversionofdoi10.1137/16M1067494
dc.relation.isversionofjnlpublisherSociety for Industrial and Applied Mathematics
dc.subject.ddclabelTraitement du signalen
dc.relation.forthcomingnonen
dc.relation.forthcomingprintnonen
dc.description.ssrncandidatenon
dc.description.halcandidatenon
dc.description.readershiprecherche
dc.description.audienceInternational
dc.relation.Isversionofjnlpeerreviewedoui
dc.date.updated2017-12-19T09:55:15Z
hal.person.labIds162010
hal.person.labIds60
hal.person.labIds162010


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record