File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Complex 3D shape recovery using a dual-space approach

TitleComplex 3D shape recovery using a dual-space approach
Authors
KeywordsComputers
Artificial intelligence
Issue Date2005
PublisherIEEE, Computer Society.
Citation
Proceedings Of The Ieee Computer Society Conference On Computer Vision And Pattern Recognition, 2005, v. 2, p. 878-884 How to Cite?
AbstractThis paper presents a novel method for reconstructing complex 3D objects with unknown topology using silhouettes extracted from image sequences. This method exploits the duality principle governing surface points and their corresponding tangent planes, and enables a direct estimation of points on the contour generators. A major problem in other related works concerns with the search for a tangent basis at singularities in the dual tangent space. This problem is addressed here by utilizing the epipolar parameterization for identifying a well-defined basis at each point, and thus avoids any form of search. For the degenerate cases where epipolar parameterization breaks up, a fast on-the-fly validation is performed for each computed surface point, which consequently leads to a significant improvement in robustness. As the resulting contour generator points are not suitable for direct triangulation, a topologically correct surface extracting method based on slicing plane is presented. Both experiments on synthetic and real world data show that the proposed method has comparable robustness as those existing volumetric methods regarding surface of complex topology, whilst producing more accurate estimation of surface points. © 2005 IEEE.
DescriptionProceeedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, v. 2, p. 878-884
Persistent Identifierhttp://hdl.handle.net/10722/45529
ISSN
References
Grants

 

DC FieldValueLanguage
dc.contributor.authorLiang, Cen_HK
dc.contributor.authorWong, KYKen_HK
dc.date.accessioned2007-10-30T06:28:32Z-
dc.date.available2007-10-30T06:28:32Z-
dc.date.issued2005en_HK
dc.identifier.citationProceedings Of The Ieee Computer Society Conference On Computer Vision And Pattern Recognition, 2005, v. 2, p. 878-884en_HK
dc.identifier.issn1063-6919en_HK
dc.identifier.urihttp://hdl.handle.net/10722/45529-
dc.descriptionProceeedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, v. 2, p. 878-884-
dc.description.abstractThis paper presents a novel method for reconstructing complex 3D objects with unknown topology using silhouettes extracted from image sequences. This method exploits the duality principle governing surface points and their corresponding tangent planes, and enables a direct estimation of points on the contour generators. A major problem in other related works concerns with the search for a tangent basis at singularities in the dual tangent space. This problem is addressed here by utilizing the epipolar parameterization for identifying a well-defined basis at each point, and thus avoids any form of search. For the degenerate cases where epipolar parameterization breaks up, a fast on-the-fly validation is performed for each computed surface point, which consequently leads to a significant improvement in robustness. As the resulting contour generator points are not suitable for direct triangulation, a topologically correct surface extracting method based on slicing plane is presented. Both experiments on synthetic and real world data show that the proposed method has comparable robustness as those existing volumetric methods regarding surface of complex topology, whilst producing more accurate estimation of surface points. © 2005 IEEE.en_HK
dc.format.extent2338714 bytes-
dc.format.extent1818 bytes-
dc.format.extent1817 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypetext/plain-
dc.format.mimetypetext/plain-
dc.languageengen_HK
dc.publisherIEEE, Computer Society.en_HK
dc.relation.ispartofProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognitionen_HK
dc.rights©2004 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.en_HK
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.subjectComputersen_HK
dc.subjectArtificial intelligenceen_HK
dc.titleComplex 3D shape recovery using a dual-space approachen_HK
dc.typeConference_Paperen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=1063-6919&volume=2&spage=878&epage=884&date=2005&atitle=Complex+3D+shape+recovery+using+a+dual-space+approachen_HK
dc.identifier.emailWong, KYK:kykwong@cs.hku.hken_HK
dc.identifier.authorityWong, KYK=rp01393en_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/CVPR.2005.104en_HK
dc.identifier.scopuseid_2-s2.0-24644494803en_HK
dc.identifier.hkuros102858-
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-24644494803&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume2en_HK
dc.identifier.spage878en_HK
dc.identifier.epage884en_HK
dc.publisher.placeUnited Statesen_HK
dc.relation.projectOutdoor 3D scanner using off-the-shelf digital camera-
dc.identifier.scopusauthoridLiang, C=54786617200en_HK
dc.identifier.scopusauthoridWong, KYK=24402187900en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats