Template Assembly for Detailed Urban Reconstruction

Handle URI:
http://hdl.handle.net/10754/556126
Title:
Template Assembly for Detailed Urban Reconstruction
Authors:
Nan, Liangliang ( 0000-0002-5629-9975 ) ; Wonka, Peter ( 0000-0003-0627-9746 ) ; Ghanem, Bernard ( 0000-0002-5534-587X ) ; Jiang, Caigui ( 0000-0002-1342-4094 )
Abstract:
We propose a new framework to reconstruct building details by automatically assembling 3D templates on coarse textured building models. In a preprocessing step, we generate an initial coarse model to approximate a point cloud computed using Structure from Motion and Multi View Stereo, and we model a set of 3D templates of facade details. Next, we optimize the initial coarse model to enforce consistency between geometry and appearance (texture images). Then, building details are reconstructed by assembling templates on the textured faces of the coarse model. The 3D templates are automatically chosen and located by our optimization-based template assembly algorithm that balances image matching and structural regularity. In the results, we demonstrate how our framework can enrich the details of coarse models using various data sets.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Publisher:
Wiley-Blackwell
Journal:
Computer Graphics Forum
Conference/Event name:
The 36th Annual Conference of the European Association for Computer Graphics
Issue Date:
4-May-2015
DOI:
10.1111/cgf.12554
Type:
Conference Paper
Additional Links:
https://dl.dropboxusercontent.com/u/18955644/website_files/template_assembly_EG2015.pdf
Appears in Collections:
Conference Papers; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorNan, Liangliangen
dc.contributor.authorWonka, Peteren
dc.contributor.authorGhanem, Bernarden
dc.contributor.authorJiang, Caiguien
dc.date.accessioned2015-06-01T15:05:07Zen
dc.date.available2015-06-01T15:05:07Zen
dc.date.issued2015-05-04en
dc.identifier.doi10.1111/cgf.12554en
dc.identifier.urihttp://hdl.handle.net/10754/556126en
dc.description.abstractWe propose a new framework to reconstruct building details by automatically assembling 3D templates on coarse textured building models. In a preprocessing step, we generate an initial coarse model to approximate a point cloud computed using Structure from Motion and Multi View Stereo, and we model a set of 3D templates of facade details. Next, we optimize the initial coarse model to enforce consistency between geometry and appearance (texture images). Then, building details are reconstructed by assembling templates on the textured faces of the coarse model. The 3D templates are automatically chosen and located by our optimization-based template assembly algorithm that balances image matching and structural regularity. In the results, we demonstrate how our framework can enrich the details of coarse models using various data sets.en
dc.publisherWiley-Blackwellen
dc.relation.urlhttps://dl.dropboxusercontent.com/u/18955644/website_files/template_assembly_EG2015.pdfen
dc.rightsArchived with thanks to EUROGRAPHICS 2015.en
dc.subjectComputer Graphicsen
dc.subjectUrban Reconstructionen
dc.titleTemplate Assembly for Detailed Urban Reconstructionen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalComputer Graphics Forumen
dc.conference.dateMay 4th-8then
dc.conference.nameThe 36th Annual Conference of the European Association for Computer Graphicsen
dc.conference.locationKongresshaus in Z├╝rich, Switzerlanden
dc.eprint.versionPost-printen
kaust.authorNan, Liangliangen
kaust.authorGhanem, Bernarden
kaust.authorWonka, Peteren
kaust.authorJiang, Caiguien
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.