File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Real-time data driven deformation with affine bones

TitleReal-time data driven deformation with affine bones
Authors
KeywordsCanonical Correlation Analysis
Deformation
Regression
Weight Smoothing
Issue Date2010
PublisherSpringer Verlag. The Journal's web site is located at http://link.springer.de/link/service/journals/00371/index.htm
Citation
Visual Computer, 2010, v. 26 n. 6-8, p. 487-495 How to Cite?
AbstractData driven deformation is increasingly important in computer graphics and interactive applications. From given mesh example sequences, we train a deformation predictor and manipulate a specific style of surface deformation interactively using only a small number of control points. The latest approach of learning the connection between rigid bone transformations and control points uses a statistically based framework, called canonical correlation analysis. In this paper, we extend this approach to a skinned mesh with affine bones, each of which conveys a nonrigid affine transformation. However, it is difficult to discover the underlying relationship between control points and nonrigid transformations. To address this issue, we present a two-layer regression framework; one layer being from control points to rigid and the other layer being from rigid to nonrigid transformations. Our contributions also include bone-vertex weight smoothing, enabling the distribution of each bone's influence across neighboring vertices. We can alleviate distortion around regions where nearby bones undergo various transformations and improve deformations reaching beyond the learned subspaces. Experimental results show that our method can achieve more general deformations including flexible muscle bulges or twists. The performance of our implementation is comparable to the latest approach. © 2010 Springer-Verlag.
Persistent Identifierhttp://hdl.handle.net/10722/152440
ISSN
2015 Impact Factor: 1.06
2015 SCImago Journal Rankings: 0.560
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorKim, BUen_US
dc.contributor.authorFeng, WWen_US
dc.contributor.authorYu, Yen_US
dc.date.accessioned2012-06-26T06:39:05Z-
dc.date.available2012-06-26T06:39:05Z-
dc.date.issued2010en_US
dc.identifier.citationVisual Computer, 2010, v. 26 n. 6-8, p. 487-495en_US
dc.identifier.issn0178-2789en_US
dc.identifier.urihttp://hdl.handle.net/10722/152440-
dc.description.abstractData driven deformation is increasingly important in computer graphics and interactive applications. From given mesh example sequences, we train a deformation predictor and manipulate a specific style of surface deformation interactively using only a small number of control points. The latest approach of learning the connection between rigid bone transformations and control points uses a statistically based framework, called canonical correlation analysis. In this paper, we extend this approach to a skinned mesh with affine bones, each of which conveys a nonrigid affine transformation. However, it is difficult to discover the underlying relationship between control points and nonrigid transformations. To address this issue, we present a two-layer regression framework; one layer being from control points to rigid and the other layer being from rigid to nonrigid transformations. Our contributions also include bone-vertex weight smoothing, enabling the distribution of each bone's influence across neighboring vertices. We can alleviate distortion around regions where nearby bones undergo various transformations and improve deformations reaching beyond the learned subspaces. Experimental results show that our method can achieve more general deformations including flexible muscle bulges or twists. The performance of our implementation is comparable to the latest approach. © 2010 Springer-Verlag.en_US
dc.languageengen_US
dc.publisherSpringer Verlag. The Journal's web site is located at http://link.springer.de/link/service/journals/00371/index.htmen_US
dc.relation.ispartofVisual Computeren_US
dc.subjectCanonical Correlation Analysisen_US
dc.subjectDeformationen_US
dc.subjectRegressionen_US
dc.subjectWeight Smoothingen_US
dc.titleReal-time data driven deformation with affine bonesen_US
dc.typeArticleen_US
dc.identifier.emailYu, Y:yzyu@cs.hku.hken_US
dc.identifier.authorityYu, Y=rp01415en_US
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.doi10.1007/s00371-010-0474-6en_US
dc.identifier.scopuseid_2-s2.0-77955770884en_US
dc.identifier.hkuros220956-
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-77955770884&selection=ref&src=s&origin=recordpageen_US
dc.identifier.volume26en_US
dc.identifier.issue6-8en_US
dc.identifier.spage487en_US
dc.identifier.epage495en_US
dc.identifier.isiWOS:000278135800010-
dc.publisher.placeGermanyen_US
dc.identifier.scopusauthoridKim, BU=24537622900en_US
dc.identifier.scopusauthoridFeng, WW=7402350996en_US
dc.identifier.scopusauthoridYu, Y=8554163500en_US
dc.identifier.citeulike7071362-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats