Show simple item record

Shape part Transfer via semantic latent space factorization

hal.structure.identifierCEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
dc.contributor.authorGroscot, Raphaël*
hal.structure.identifierCEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
dc.contributor.authorCohen, Laurent D.
HAL ID: 738939		*
hal.structure.identifier
dc.contributor.authorGuibas, Leonidas*
dc.date.accessioned2019-10-12T14:24:56Z
dc.date.available2019-10-12T14:24:56Z
dc.date.issued2019
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/20118
dc.language.isoenen
dc.subjectAutoencoder
dc.subjectPointcloud
dc.subjectLatent space
dc.subject.ddc621.3en
dc.titleShape part Transfer via semantic latent space factorization
dc.typeCommunication / Conférence
dc.description.abstractenWe present a latent space factorization that controls a generative neural network for shapes in a semantic way. Our method uses the segmentation data present in a collection of shapes to explicitly factorize the encoder of a pointcloud autoencoder network, replacing it by several sub-encoders. This allows to learn a semantically-structured latent space in which we can uncover statistical modes corresponding to semantically similar shapes, as well as mixing parts from several objects to create hybrids and quickly explore design ideas through varying shape combinations. Our work differs from existing methods in two ways: first, it proves the usefulness of neural networks to achieve shape combinations and second, adapts the whole geometry of the object to accommodate for its different parts.
dc.identifier.citationpages511-519
dc.relation.ispartoftitleGeometric Science of Information 4th International Conference, GSI 2019, Toulouse, France, August 27–29, 2019, Proceedings
dc.relation.ispartoftitleProc. 4th conference on Geometric Science of Information (GSI2019)
dc.relation.ispartofpublnameSpringer
dc.relation.ispartofpublcityBerlin Heidelberg
dc.relation.ispartofdate2019
dc.relation.ispartofurl10.1007/978-3-030-26980-7
dc.subject.ddclabelTraitement du signalen
dc.relation.ispartofisbnPrint ISBN 978-3-030-26979-1
dc.relation.confcountryFRANCE
dc.relation.forthcomingnonen
dc.identifier.doi10.1007/978-3-030-26980-7_53
dc.description.ssrncandidatenon
dc.description.halcandidatenon
dc.description.readershiprecherche
dc.description.audienceInternational
dc.date.updated2019-10-12T14:25:31Z
hal.author.functionaut
hal.author.functionaut
hal.author.functionaut


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record