Interactive design of probability density functions for shape grammars

Handle URI:
http://hdl.handle.net/10754/592887
Title:
Interactive design of probability density functions for shape grammars
Authors:
Dang, Minh; Lienhard, Stefan; Ceylan, Duygu; Neubert, Boris; Wonka, Peter ( 0000-0003-0627-9746 ) ; Pauly, Mark
Abstract:
A shape grammar defines a procedural shape space containing a variety of models of the same class, e.g. buildings, trees, furniture, airplanes, bikes, etc. We present a framework that enables a user to interactively design a probability density function (pdf) over such a shape space and to sample models according to the designed pdf. First, we propose a user interface that enables a user to quickly provide preference scores for selected shapes and suggest sampling strategies to decide which models to present to the user to evaluate. Second, we propose a novel kernel function to encode the similarity between two procedural models. Third, we propose a framework to interpolate user preference scores by combining multiple techniques: function factorization, Gaussian process regression, autorelevance detection, and l1 regularization. Fourth, we modify the original grammars to generate models with a pdf proportional to the user preference scores. Finally, we provide evaluations of our user interface and framework parameters and a comparison to other exploratory modeling techniques using modeling tasks in five example shape spaces: furniture, low-rise buildings, skyscrapers, airplanes, and vegetation.
KAUST Department:
Visual Computing Center (VCC)
Citation:
Interactive design of probability density functions for shape grammars 2015, 34 (6):1 ACM Transactions on Graphics
Publisher:
Association for Computing Machinery (ACM)
Conference/Event name:
Proceedings of ACM SIGGRAPH Asia 2015
Issue Date:
2-Nov-2015
DOI:
10.1145/2816795.2818069
Type:
Conference Paper
ISSN:
07300301
Additional Links:
http://dl.acm.org/citation.cfm?doid=2816795.2818069
Appears in Collections:
Conference Papers; Visual Computing Center (VCC)

Full metadata record

DC FieldValue Language
dc.contributor.authorDang, Minhen
dc.contributor.authorLienhard, Stefanen
dc.contributor.authorCeylan, Duyguen
dc.contributor.authorNeubert, Borisen
dc.contributor.authorWonka, Peteren
dc.contributor.authorPauly, Marken
dc.date.accessioned2016-01-06T06:07:42Zen
dc.date.available2016-01-06T06:07:42Zen
dc.date.issued2015-11-02en
dc.identifier.citationInteractive design of probability density functions for shape grammars 2015, 34 (6):1 ACM Transactions on Graphicsen
dc.identifier.issn07300301en
dc.identifier.doi10.1145/2816795.2818069en
dc.identifier.urihttp://hdl.handle.net/10754/592887en
dc.description.abstractA shape grammar defines a procedural shape space containing a variety of models of the same class, e.g. buildings, trees, furniture, airplanes, bikes, etc. We present a framework that enables a user to interactively design a probability density function (pdf) over such a shape space and to sample models according to the designed pdf. First, we propose a user interface that enables a user to quickly provide preference scores for selected shapes and suggest sampling strategies to decide which models to present to the user to evaluate. Second, we propose a novel kernel function to encode the similarity between two procedural models. Third, we propose a framework to interpolate user preference scores by combining multiple techniques: function factorization, Gaussian process regression, autorelevance detection, and l1 regularization. Fourth, we modify the original grammars to generate models with a pdf proportional to the user preference scores. Finally, we provide evaluations of our user interface and framework parameters and a comparison to other exploratory modeling techniques using modeling tasks in five example shape spaces: furniture, low-rise buildings, skyscrapers, airplanes, and vegetation.en
dc.publisherAssociation for Computing Machinery (ACM)en
dc.relation.urlhttp://dl.acm.org/citation.cfm?doid=2816795.2818069en
dc.rightsArchived with thanks to ACM Transactions on Graphicsen
dc.titleInteractive design of probability density functions for shape grammarsen
dc.typeConference Paperen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.conference.date2-5 November 2015en
dc.conference.nameProceedings of ACM SIGGRAPH Asia 2015en
dc.conference.locationthe Kobe Convention Center, Kobe, Japanen
dc.eprint.versionPublisher's Version/PDFen
dc.contributor.institutionEPFLen
dc.contributor.institutionAdobe Researchen
dc.contributor.institutionKITen
kaust.authorWonka, Peteren
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.