Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Content-based retrieval of 3D models using generative modeling techniques

: Grabner, Harald; Ullrich, Torsten; Fellner, Dieter W.


Klein, Reinhard (Ed.); Santos, Pedro (Ed.); Fellner, Dieter W. (Event Co-Chair); Scopigno, Roberto (Event Co-Chair) ; TU Graz, Institut für ComputerGraphik und WissensVisualisierung -CGV-; Fraunhofer-Institut für Graphische Datenverarbeitung -IGD-, Darmstadt; European Association for Computer Graphics -EUROGRAPHICS-:
Eurographics Workshop on Graphics and Cultural Heritage, GHC 2014. Short Papers - Posters : Darmstadt, Germany, October 6 - 8, 2014
Goslar: Eurographics Association, 2014
ISBN: 978-3-905674-75-0
Workshop on Graphics and Cultural Heritage (GHC) <12, 2014, Darmstadt>
Conference Paper
Fraunhofer IGD ()
computer graphics; information systems; content based retrieval; knowledge representation; scene analysis; object recognition; generative modeling; Business Field: Digital society; Research Area: Modeling (MOD); Forschungsgruppe Semantic Models, Immersive Systems (SMIS)

In 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.