Show simple item record

dc.contributor.authorGrabner, Haralden_US
dc.contributor.authorUllrich, Torstenen_US
dc.contributor.authorFellner, Dieter W.en_US
dc.contributor.editorReinhard Klein and Pedro Santosen_US
dc.date.accessioned2014-12-16T07:24:49Z
dc.date.available2014-12-16T07:24:49Z
dc.date.issued2014en_US
dc.identifier.isbn978-3-905674-75-0en_US
dc.identifier.urihttp://dx.doi.org/10.2312/gch.20141317en_US
dc.description.abstractIn this paper we present a novel 3D model retrieval approach based on generative modeling techniques. In our approach generative models are created by domain experts in order to describe 3D model classes. These generative models span a shape space, of which a number of training samples is taken at random. The samples are used to train content-based retrieval methods. With a trained classifier, techniques based on semantic enrichment can be used to index a repository. Furthermore, as our method uses solely generative 3D models in the training phase, it eliminates the cold start problem. We demonstrate the effectiveness of our method by testing it against the Princeton shape benchmark.en_US
dc.publisherThe Eurographics Associationen_US
dc.subjectH.3.3 [Computer Graphics]en_US
dc.subjectInformation Systemsen_US
dc.subjectInformation Search and Retrievalen_US
dc.subjectI.2.4 [Computer Graphics]en_US
dc.subjectKnowledge Representation Formalisms and Methodsen_US
dc.subjectRepresentations (procedural and ruleen_US
dc.subjectbased)en_US
dc.subjectI.4.8 [Computer Graphics]en_US
dc.subjectScene Analysisen_US
dc.subjectObject recognitionen_US
dc.titleContent-based Retrieval of 3D Models using Generative Modeling Techniquesen_US
dc.description.seriesinformationEurographics Workshop on Graphics and Cultural Heritage - Short Papers / Postersen_US


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record