Inverse procedural modeling of facade layouts

Handle URI:
http://hdl.handle.net/10754/575793
Title:
Inverse procedural modeling of facade layouts
Authors:
Wu, Fuzhang; Yan, Dongming ( 0000-0003-2209-2404 ) ; Dong, Weiming; Zhang, Xiaopeng; Wonka, Peter ( 0000-0003-0627-9746 )
Abstract:
In this paper, we address the following research problem: How can we generate a meaningful split grammar that explains a given facade layout? To evaluate if a grammar is meaningful, we propose a cost function based on the description length and minimize this cost using an approximate dynamic programming framework. Our evaluation indicates that our framework extracts meaningful split grammars that are competitive with those of expert users, while some users and all competing automatic solutions are less successful. Copyright © ACM.
KAUST Department:
Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Computer Science Program
Publisher:
Association for Computing Machinery (ACM)
Conference/Event name:
41st International Conference and Exhibition on Computer Graphics and Interactive Techniques, ACM SIGGRAPH 2014
Issue Date:
27-Jul-2014
DOI:
10.1145/2601097.2601162
ARXIV:
arXiv:1308.0419v2
Type:
Conference Paper
ISSN:
07342071
Sponsors:
This research was partially funded by the Visual Computing Center of King Abdullah University of Science and Technology (KAUST), the National Natural Science Foundation of China (no. 61372168, 61172104, 61331018, and 61372184), and the U.S. National Science Foundation (no. 0643822). We thank Yoshihiro Kobayashi for helping with the 3D renderings and Virginia Unkefer for proof-reading.
Appears in Collections:
Conference Papers; Computer Science Program; Computer Science Program; Visual Computing Center (VCC); Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorWu, Fuzhangen
dc.contributor.authorYan, Dongmingen
dc.contributor.authorDong, Weimingen
dc.contributor.authorZhang, Xiaopengen
dc.contributor.authorWonka, Peteren
dc.date.accessioned2015-08-24T09:26:21Zen
dc.date.available2015-08-24T09:26:21Zen
dc.date.issued2014-07-27en
dc.identifier.issn07342071en
dc.identifier.doi10.1145/2601097.2601162en
dc.identifier.urihttp://hdl.handle.net/10754/575793en
dc.description.abstractIn this paper, we address the following research problem: How can we generate a meaningful split grammar that explains a given facade layout? To evaluate if a grammar is meaningful, we propose a cost function based on the description length and minimize this cost using an approximate dynamic programming framework. Our evaluation indicates that our framework extracts meaningful split grammars that are competitive with those of expert users, while some users and all competing automatic solutions are less successful. Copyright © ACM.en
dc.description.sponsorshipThis research was partially funded by the Visual Computing Center of King Abdullah University of Science and Technology (KAUST), the National Natural Science Foundation of China (no. 61372168, 61172104, 61331018, and 61372184), and the U.S. National Science Foundation (no. 0643822). We thank Yoshihiro Kobayashi for helping with the 3D renderings and Virginia Unkefer for proof-reading.en
dc.publisherAssociation for Computing Machinery (ACM)en
dc.subjectFacadesen
dc.subjectInverse procedural modelingen
dc.subjectProcedural modelingen
dc.subjectShape grammarsen
dc.subjectUrban modelingen
dc.titleInverse procedural modeling of facade layoutsen
dc.typeConference Paperen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentComputer Science Programen
dc.conference.date10 August 2014 through 14 August 2014en
dc.conference.name41st International Conference and Exhibition on Computer Graphics and Interactive Techniques, ACM SIGGRAPH 2014en
dc.conference.locationVancouver, BCen
dc.contributor.institutionLIAMA-NLPR, CAS Institute of Automation, Chinaen
dc.contributor.institutionArizona State Univ., United Statesen
dc.identifier.arxividarXiv:1308.0419v2en
kaust.authorYan, Dongmingen
kaust.authorWonka, Peteren
kaust.authorWu, Fuzhangen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.