Handle URI:
http://hdl.handle.net/10754/597382
Title:
A probabilistic model for component-based shape synthesis
Authors:
Kalogerakis, Evangelos; Chaudhuri, Siddhartha; Koller, Daphne; Koltun, Vladlen
Abstract:
We present an approach to synthesizing shapes from complex domains, by identifying new plausible combinations of components from existing shapes. Our primary contribution is a new generative model of component-based shape structure. The model represents probabilistic relationships between properties of shape components, and relates them to learned underlying causes of structural variability within the domain. These causes are treated as latent variables, leading to a compact representation that can be effectively learned without supervision from a set of compatibly segmented shapes. We evaluate the model on a number of shape datasets with complex structural variability and demonstrate its application to amplification of shape databases and to interactive shape synthesis. © 2012 ACM 0730-0301/2012/08-ART55.
Citation:
Kalogerakis E, Chaudhuri S, Koller D, Koltun V (2012) A probabilistic model for component-based shape synthesis. ACM Transactions on Graphics 31: 1–11. Available: http://dx.doi.org/10.1145/2185520.2185551.
Publisher:
Association for Computing Machinery (ACM)
Journal:
ACM Transactions on Graphics
Issue Date:
1-Jul-2012
DOI:
10.1145/2185520.2185551
Type:
Article
ISSN:
0730-0301
Sponsors:
We are grateful to Aaron Hertzmann, Sergey Levine, and Philipp Krahenbuhl for their comments on this paper, and to Tom Funkhouser for helpful discussions. This research was conducted in conjunction with the Intel Science and Technology Center for Visual Computing, and was supported in part by KAUST Global Collaborative Research and by NSF grants SES-0835601 and CCF-0641402.
Appears in Collections:
Publications Acknowledging KAUST Support

Full metadata record

DC FieldValue Language
dc.contributor.authorKalogerakis, Evangelosen
dc.contributor.authorChaudhuri, Siddharthaen
dc.contributor.authorKoller, Daphneen
dc.contributor.authorKoltun, Vladlenen
dc.date.accessioned2016-02-25T12:32:04Zen
dc.date.available2016-02-25T12:32:04Zen
dc.date.issued2012-07-01en
dc.identifier.citationKalogerakis E, Chaudhuri S, Koller D, Koltun V (2012) A probabilistic model for component-based shape synthesis. ACM Transactions on Graphics 31: 1–11. Available: http://dx.doi.org/10.1145/2185520.2185551.en
dc.identifier.issn0730-0301en
dc.identifier.doi10.1145/2185520.2185551en
dc.identifier.urihttp://hdl.handle.net/10754/597382en
dc.description.abstractWe present an approach to synthesizing shapes from complex domains, by identifying new plausible combinations of components from existing shapes. Our primary contribution is a new generative model of component-based shape structure. The model represents probabilistic relationships between properties of shape components, and relates them to learned underlying causes of structural variability within the domain. These causes are treated as latent variables, leading to a compact representation that can be effectively learned without supervision from a set of compatibly segmented shapes. We evaluate the model on a number of shape datasets with complex structural variability and demonstrate its application to amplification of shape databases and to interactive shape synthesis. © 2012 ACM 0730-0301/2012/08-ART55.en
dc.description.sponsorshipWe are grateful to Aaron Hertzmann, Sergey Levine, and Philipp Krahenbuhl for their comments on this paper, and to Tom Funkhouser for helpful discussions. This research was conducted in conjunction with the Intel Science and Technology Center for Visual Computing, and was supported in part by KAUST Global Collaborative Research and by NSF grants SES-0835601 and CCF-0641402.en
dc.publisherAssociation for Computing Machinery (ACM)en
dc.subjectData-driven 3D modelingen
dc.subjectMachine learningen
dc.subjectProbabilistic graphical modelsen
dc.subjectShape structureen
dc.subjectShape synthesisen
dc.titleA probabilistic model for component-based shape synthesisen
dc.typeArticleen
dc.identifier.journalACM Transactions on Graphicsen
dc.contributor.institutionStanford University, Palo Alto, United Statesen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.