Show simple item record

Constrained Sparse Texture Synthesis

hal.structure.identifier
dc.contributor.authorTartavel, Guillaume*
hal.structure.identifier
dc.contributor.authorGousseau, Yann*
hal.structure.identifier
dc.contributor.authorPeyré, Gabriel
HAL ID: 1211		*
dc.date.accessioned2013-03-16T09:22:03Z
dc.date.available2013-03-16T09:22:03Z
dc.date.issued2013
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/11134
dc.descriptionLNCS n°7893
dc.language.isoenen
dc.subjectsparse decomposition
dc.subjecttexture synthesis
dc.subjectvariational methods
dc.subjectdictionary learning
dc.subject.ddc006.3en
dc.titleConstrained Sparse Texture Synthesis
dc.typeCommunication / Conférence
dc.description.abstractenThis paper presents a novel texture synthesis algorithm that performs a sparse expansion of the patches of the image in a dictionary learned from an input exemplar. The synthesized texture is computed through the minimization of a non-convex energy that takes into account several constraints. Our first contribution is the computation of a sparse expansion of the patches imposing that the dictionary atoms are used in the same proportions as in the exemplar. This is crucial to enable a fair representation of the features of the input image during the synthesis process. Our second contribution is the use of additional penalty terms in the variational formulation to maintain the histogram and the low frequency content of the input. Lastly we introduce a non-linear re construction process that stitches together patches without introducing blur. Numerical results illustrate the importance of each of these contributions to achieve state of the art texture synthesis.
dc.identifier.citationpages186-197
dc.relation.ispartoftitleScale Space and Variational Methods in Computer Vision 4th International Conference, SSVM 2013, Schloss Seggau, Leibnitz, Austria, June 2-6, 2013. Proceedings
dc.relation.ispartofeditorArjan Kuijper; Kristian Bredies; Thomas Pock; Horst Bischof
dc.relation.ispartofpublnameSpringer
dc.relation.ispartofpublcityBerlin Heidelberg
dc.relation.ispartofdate2013
dc.relation.ispartofurl10.1007/978-3-642-38267-3
dc.subject.ddclabelIntelligence artificielleen
dc.relation.ispartofisbn978-3-642-3826
dc.relation.confcountryAUSTRIA
dc.identifier.doi10.1007/978-3-642-38267-3_16
dc.description.ssrncandidatenon
dc.description.halcandidateoui
dc.description.readershiprecherche
dc.description.audienceInternational
dc.date.updated2018-01-08T15:11:31Z
hal.author.functionaut
hal.author.functionaut
hal.author.functionaut


Files in this item

Thumbnail
Name:
SparseSynthesis.pdf
Size:
2.151Mb
Format:
PDF
View/Open

This item appears in the following Collection(s)

Show simple item record