Coupled structure-from-motion and 3D symmetry detection for urban facades

Handle URI:
http://hdl.handle.net/10754/563322
Title:
Coupled structure-from-motion and 3D symmetry detection for urban facades
Authors:
Ceylan, Duygu; Mitra, Niloy J. ( 0000-0002-2597-0914 ) ; Zheng, Youyi; Pauly, Mark
Abstract:
Repeated structures are ubiquitous in urban facades. Such repetitions lead to ambiguity in establishing correspondences across sets of unordered images. A decoupled structure-from-motion reconstruction followed by symmetry detection often produces errors: outputs are either noisy and incomplete, or even worse, appear to be valid but actually have a wrong number of repeated elements.We present an optimization framework for extracting repeated elements in images of urban facades, while simultaneously calibrating the input images and recovering the 3D scene geometry using a graph-based global analysis. We evaluate the robustness of the proposed scheme on a range of challenging examples containing widespread repetitions and nondistinctive features. These image sets are common but cannot be handled well with state-of-the-art methods. We show that the recovered symmetry information along with the 3D geometry enables a range of novel image editing operations that maintain consistency across the images. © 2014 ACM 0730-0301/2014/01-ART3 15.00.
KAUST Department:
Visual Computing Center (VCC)
Publisher:
Association for Computing Machinery (ACM)
Journal:
ACM Transactions on Graphics
Issue Date:
1-Jan-2014
DOI:
10.1145/2517348
Type:
Article
ISSN:
07300301
Sponsors:
This research received funding from the European Research Council under the European Unions 7th Framework Programme (FP/2007-2013)/ERC Grant Agreement 257453, ERC Starting Grant COSYM and European Community's Research Infrastructure Action grant agreement VISIONAIR 262044 under the 7th Framework Programme (FP7/2007-2013). This research was also supported by a Marie Curie CIG, an Adobe Research grant, and a UCL impact award.
Appears in Collections:
Articles; Visual Computing Center (VCC)

Full metadata record

DC FieldValue Language
dc.contributor.authorCeylan, Duyguen
dc.contributor.authorMitra, Niloy J.en
dc.contributor.authorZheng, Youyien
dc.contributor.authorPauly, Marken
dc.date.accessioned2015-08-03T11:45:42Zen
dc.date.available2015-08-03T11:45:42Zen
dc.date.issued2014-01-01en
dc.identifier.issn07300301en
dc.identifier.doi10.1145/2517348en
dc.identifier.urihttp://hdl.handle.net/10754/563322en
dc.description.abstractRepeated structures are ubiquitous in urban facades. Such repetitions lead to ambiguity in establishing correspondences across sets of unordered images. A decoupled structure-from-motion reconstruction followed by symmetry detection often produces errors: outputs are either noisy and incomplete, or even worse, appear to be valid but actually have a wrong number of repeated elements.We present an optimization framework for extracting repeated elements in images of urban facades, while simultaneously calibrating the input images and recovering the 3D scene geometry using a graph-based global analysis. We evaluate the robustness of the proposed scheme on a range of challenging examples containing widespread repetitions and nondistinctive features. These image sets are common but cannot be handled well with state-of-the-art methods. We show that the recovered symmetry information along with the 3D geometry enables a range of novel image editing operations that maintain consistency across the images. © 2014 ACM 0730-0301/2014/01-ART3 15.00.en
dc.description.sponsorshipThis research received funding from the European Research Council under the European Unions 7th Framework Programme (FP/2007-2013)/ERC Grant Agreement 257453, ERC Starting Grant COSYM and European Community's Research Infrastructure Action grant agreement VISIONAIR 262044 under the 7th Framework Programme (FP7/2007-2013). This research was also supported by a Marie Curie CIG, an Adobe Research grant, and a UCL impact award.en
dc.publisherAssociation for Computing Machinery (ACM)en
dc.subject3D reconstructionen
dc.subjectCoupled editingen
dc.subjectImage collectionsen
dc.subjectStructure-from-motionen
dc.subjectSymmetry detectionen
dc.titleCoupled structure-from-motion and 3D symmetry detection for urban facadesen
dc.typeArticleen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.identifier.journalACM Transactions on Graphicsen
dc.contributor.institutionEPFL, Route Cantonale, 1015 Lausanne, Switzerlanden
dc.contributor.institutionUniversity College London, Gower St, London WC1E 6BT, United Kingdomen
kaust.authorZheng, Youyien
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.