Conference Paper: Robust and unbiased foreground / background energy for multi-view stereo

File Download Links for fulltext
(May Require Subscription)
Supplementary

  • Basic View
  • Metadata View
  • XML View
TitleRobust and unbiased foreground / background energy for multi-view stereo
AuthorsChen, Z1
Wong, KYK1
KeywordsForeground / background energy
Graph-cuts
Multi-view stereo
Photo-consistency energy
Issue Date2011
CitationThe International Joint Conference on Computer Vision Theory and Applications (VISAPP 2011), Vilamoura, Algarve, Portugal, 5-7 March 2011. In Proceedings of VISAPP, 2011, p. 451-458 [How to Cite?]
AbstractThis paper revisits the graph-cuts based approach for solving the multi-view stereo problem, and proposes a novel foreground / background energy which is shown to be unbiased and robust against noisy depth maps. Unlike most existing works which focus on deriving a robust photo-consistency energy, this paper targets at deriving a robust and unbiased foreground / background energy. By introducing a novel data-dependent foreground / background energy, we show that it is possible to recover the object surface from noisy depth maps even in the absence of the photo-consistency energy. This demonstrates that the foreground / background energy is equally important as the photo-consistency energy in graph-cuts based methods. Experiments on real data sequences further show that high quality reconstructions can be achieved using our proposed foreground / background energy with a very simple photo-consistency energy.
DescriptionArea 3 - Motion, Tracking and Stereo Vision: Paper no. 13
VISAPP is part of VISIGRAPP - International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
ISBN9789898425478
ReferencesReferences in Scopus
DC Field
Value
dc.contributor.authorChen, Z
dc.contributor.authorWong, KYK
dc.date.accessioned2011-08-26T14:30:32Z
dc.date.available2011-08-26T14:30:32Z
dc.date.issued2011
dc.description.abstractThis paper revisits the graph-cuts based approach for solving the multi-view stereo problem, and proposes a novel foreground / background energy which is shown to be unbiased and robust against noisy depth maps. Unlike most existing works which focus on deriving a robust photo-consistency energy, this paper targets at deriving a robust and unbiased foreground / background energy. By introducing a novel data-dependent foreground / background energy, we show that it is possible to recover the object surface from noisy depth maps even in the absence of the photo-consistency energy. This demonstrates that the foreground / background energy is equally important as the photo-consistency energy in graph-cuts based methods. Experiments on real data sequences further show that high quality reconstructions can be achieved using our proposed foreground / background energy with a very simple photo-consistency energy.
dc.description.natureLink_to_subscribed_fulltext
dc.descriptionArea 3 - Motion, Tracking and Stereo Vision: Paper no. 13
dc.descriptionVISAPP is part of VISIGRAPP - International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
dc.description.otherThe International Joint Conference on Computer Vision Theory and Applications (VISAPP 2011), Vilamoura, Algarve, Portugal, 5-7 March 2011. In Proceedings of VISAPP, 2011, p. 451-458
dc.identifier.citationThe International Joint Conference on Computer Vision Theory and Applications (VISAPP 2011), Vilamoura, Algarve, Portugal, 5-7 March 2011. In Proceedings of VISAPP, 2011, p. 451-458 [How to Cite?]
dc.identifier.epage458
dc.identifier.hkuros191681
dc.identifier.isbn9789898425478
dc.identifier.openurl
dc.identifier.scopuseid_2-s2.0-79960175596
dc.identifier.spage451
dc.identifier.urihttp://hdl.handle.net/10722/137651
dc.languageeng
dc.relation.ispartofProceedings of the International Conference on Computer Vision Theory and Application, VISAPP 2011
dc.relation.referencesReferences in Scopus
dc.subjectForeground / background energy
dc.subjectGraph-cuts
dc.subjectMulti-view stereo
dc.subjectPhoto-consistency energy
dc.titleRobust and unbiased foreground / background energy for multi-view stereo
dc.typeConference_Paper
Author Affiliations
  1. The University of Hong Kong