Recurring part arrangements in shape collections

Handle URI:
http://hdl.handle.net/10754/575714
Title:
Recurring part arrangements in shape collections
Authors:
Zheng, Youyi; Cohen-Or, Daniel; Averkiou, Melinos; Mitra, Niloy J. ( 0000-0002-2597-0914 )
Abstract:
Extracting semantically related parts across models remains challenging, especially without supervision. The common approach is to co-analyze a model collection, while assuming the existence of descriptive geometric features that can directly identify related parts. In the presence of large shape variations, common geometric features, however, are no longer sufficiently descriptive. In this paper, we explore an indirect top-down approach, where instead of part geometry, part arrangements extracted from each model are compared. The key observation is that while a direct comparison of part geometry can be ambiguous, part arrangements, being higher level structures, remain consistent, and hence can be used to discover latent commonalities among semantically related shapes. We show that our indirect analysis leads to the detection of recurring arrangements of parts, which are otherwise difficult to discover in a direct unsupervised setting. We evaluate our algorithm on ground truth datasets and report advantages over geometric similarity-based bottom-up co-segmentation algorithms. © 2014 The Author(s) Computer Graphics Forum © 2014 The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd.
KAUST Department:
Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Publisher:
Wiley-Blackwell
Journal:
Computer Graphics Forum
Issue Date:
May-2014
DOI:
10.1111/cgf.12309
Type:
Article
ISSN:
01677055
Sponsors:
We thank the anonymous reviewers and Maks Ovsjanikov for their valuable comments. We thank Qixing Huang, Vladimir Kim, Ligang Liu for their help with comparison; Bongjin Koo for proofreading the paper, and Charlotte Rakhit for the video voice over. This work is supported in part by ISF, Marie Curie CIG, and ERC Starting Grant SmartGeometry.
Appears in Collections:
Articles; 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.authorZheng, Youyien
dc.contributor.authorCohen-Or, Danielen
dc.contributor.authorAverkiou, Melinosen
dc.contributor.authorMitra, Niloy J.en
dc.date.accessioned2015-08-24T08:36:25Zen
dc.date.available2015-08-24T08:36:25Zen
dc.date.issued2014-05en
dc.identifier.issn01677055en
dc.identifier.doi10.1111/cgf.12309en
dc.identifier.urihttp://hdl.handle.net/10754/575714en
dc.description.abstractExtracting semantically related parts across models remains challenging, especially without supervision. The common approach is to co-analyze a model collection, while assuming the existence of descriptive geometric features that can directly identify related parts. In the presence of large shape variations, common geometric features, however, are no longer sufficiently descriptive. In this paper, we explore an indirect top-down approach, where instead of part geometry, part arrangements extracted from each model are compared. The key observation is that while a direct comparison of part geometry can be ambiguous, part arrangements, being higher level structures, remain consistent, and hence can be used to discover latent commonalities among semantically related shapes. We show that our indirect analysis leads to the detection of recurring arrangements of parts, which are otherwise difficult to discover in a direct unsupervised setting. We evaluate our algorithm on ground truth datasets and report advantages over geometric similarity-based bottom-up co-segmentation algorithms. © 2014 The Author(s) Computer Graphics Forum © 2014 The Eurographics Association and John Wiley & Sons Ltd. Published by John Wiley & Sons Ltd.en
dc.description.sponsorshipWe thank the anonymous reviewers and Maks Ovsjanikov for their valuable comments. We thank Qixing Huang, Vladimir Kim, Ligang Liu for their help with comparison; Bongjin Koo for proofreading the paper, and Charlotte Rakhit for the video voice over. This work is supported in part by ISF, Marie Curie CIG, and ERC Starting Grant SmartGeometry.en
dc.publisherWiley-Blackwellen
dc.titleRecurring part arrangements in shape collectionsen
dc.typeArticleen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalComputer Graphics Forumen
dc.contributor.institutionTel Aviv University, Israelen
dc.contributor.institutionUniversity College London, United Kingdomen
kaust.authorZheng, Youyien
kaust.authorMitra, Niloy J.en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.