Show simple item record

dc.contributor.authorHuang, Ruqi
dc.contributor.authorRen, Jing
dc.contributor.authorWonka, Peter
dc.contributor.authorOvsjanikov, Maks
dc.date.accessioned2020-08-23T10:15:32Z
dc.date.available2020-08-23T10:15:32Z
dc.date.issued2020-08-12
dc.identifier.citationHuang, R., Ren, J., Wonka, P., & Ovsjanikov, M. (2020). C onsistent Z oom O ut  : Efficient Spectral Map Synchronization. Computer Graphics Forum, 39(5), 265–278. doi:10.1111/cgf.14084
dc.identifier.issn1467-8659
dc.identifier.issn0167-7055
dc.identifier.doi10.1111/cgf.14084
dc.identifier.urihttp://hdl.handle.net/10754/664764
dc.description.abstractIn this paper, we propose a novel method, which we call Consistent ZoomOut, for efficiently refining correspondences among deformable 3D shape collections, while promoting the resulting map consistency. Our formulation is closely related to a recent unidirectional spectral refinement framework, but naturally integrates map consistency constraints into the refinement. Beyond that, we show further that our formulation can be adapted to recover the underlying isometry among near-isometric shape collections with a theoretical guarantee, which is absent in the other spectral map synchronization frameworks. We demonstrate that our method improves the accuracy compared to the competing methods when synchronizing correspondences in both near-isometric and heterogeneous shape collections, but also significantly outperforms the baselines in terms of map consistency.
dc.description.sponsorshipThe authors thank the anonymous reviewers for their valuable comments. Parts of this work were supported by the KAUST OSR Award No. CRG-2017-3426 and the ERC Starting Grant No. 758800 (EXPROTEA).
dc.publisherWiley
dc.relation.urlhttps://onlinelibrary.wiley.com/doi/abs/10.1111/cgf.14084
dc.rightsArchived with thanks to Computer Graphics Forum
dc.titleConsistent ZoomOut: Efficient Spectral Map Synchronization
dc.typeArticle
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentVisual Computing Center (VCC)
dc.identifier.journalComputer Graphics Forum
dc.rights.embargodate2021-08-13
dc.eprint.versionPost-print
dc.contributor.institutionLIX, École Polytechnique, CNRS
dc.identifier.volume39
dc.identifier.issue5
dc.identifier.pages265-278
kaust.personRen, Jing
kaust.personWonka, Peter
kaust.grant.numberCRG-2017-3426
dc.identifier.eid2-s2.0-85089373049
refterms.dateFOA2020-08-23T12:51:30Z
kaust.acknowledged.supportUnitOSR
dc.date.published-online2020-08-12
dc.date.published-print2020-08


Files in this item

Thumbnail
Name:
CZO_SGP2020.pdf
Size:
33.14Mb
Format:
PDF
Description:
Accepted manuscript

This item appears in the following Collection(s)

Show simple item record