Afficher la notice abrégée

Optimal transport between GMM for multiscale texture synthesis

hal.structure.identifierMathématiques Appliquées Paris 5 [MAP5 - UMR 8145]
dc.contributor.authorDELON, Julie
hal.structure.identifierCB - Centre Borelli - UMR 9010 [CB]
dc.contributor.authorDESOLNEUX, Agnès
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
dc.contributor.authorFACQ, Laurent
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
dc.contributor.authorLECLAIRE, Arthur
dc.date.accessioned2024-04-04T02:34:15Z
dc.date.available2024-04-04T02:34:15Z
dc.date.conference2023-05-21
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/190537
dc.description.abstractEnUsing optimal transport in image processing tasks has become very popular. However, it still faces difficult computational issues when dealing with high-dimensional distributions. We propose here to use the recently introduced GMM-OT formulation, which consists in restricting the optimal transport problem to the set of Gaussian mixture models. As a proof of concept, we use it to improve the texture model Texto based on optimal transport between distributions of image patches. Using GMM-OT in this texture model allows to deal with larger patches, hence providing results with better geometric details. This new model allows for synthesis, mixing, and style transfer.
dc.language.isoen
dc.publisherSpringer
dc.source.titleLecture Notes in Computer ScienceScale Space and Variational Methods in Computer Vision9th International Conference, SSVM 2023, Santa Margherita di Pula, Italy, May 21–25, 2023, Proceedings
dc.subject.enOptimal transport
dc.subject.enGaussian mixture models
dc.subject.enTexture synthesis
dc.title.enOptimal transport between GMM for multiscale texture synthesis
dc.typeCommunication dans un congrès
dc.identifier.doi10.1007/978-3-031-31975-4_48
dc.subject.halSciences de l'ingénieur [physics]/Traitement du signal et de l'image
dc.subject.halMathématiques [math]/Optimisation et contrôle [math.OC]
dc.subject.halMathématiques [math]/Statistiques [math.ST]
bordeaux.hal.laboratoriesInstitut de Mathématiques de Bordeaux (IMB) - UMR 5251*
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
bordeaux.conference.titleInternational Conference on Scale Space and Variational Methods in Computer Vision (SSVM)
bordeaux.countryIT
bordeaux.title.proceedingLecture Notes in Computer ScienceScale Space and Variational Methods in Computer Vision9th International Conference, SSVM 2023, Santa Margherita di Pula, Italy, May 21–25, 2023, Proceedings
bordeaux.conference.cityCagliari
bordeaux.peerReviewedoui
hal.identifierhal-03613622
hal.version1
hal.invitednon
hal.proceedingsoui
hal.conference.organizerLuca Calatroni
hal.conference.organizerMarco Donatelli
hal.conference.organizerSerena Morigi
hal.conference.organizerMarco Prato
hal.conference.organizerGiuseppe Rodriguez
hal.conference.organizerMatteo Santacesaria
hal.conference.end2023-05-25
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-03613622v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.btitle=Lecture%20Notes%20in%20Computer%20ScienceScale%20Space%20and%20Variational%20Methods%20in%20Computer%20Vision9th%20International%20Conference,%20SSVM%202023,%20Santa%20M&rft.au=DELON,%20Julie&DESOLNEUX,%20Agn%C3%A8s&FACQ,%20Laurent&LECLAIRE,%20Arthur&rft.genre=unknown


Fichier(s) constituant ce document

FichiersTailleFormatVue

Il n'y a pas de fichiers associés à ce document.

Ce document figure dans la(les) collection(s) suivante(s)

Afficher la notice abrégée