File Download
  • No File Attached
 
Links for fulltext
(May Require Subscription)
 
Supplementary

Conference Paper: Real-time data driven deformation using kernel canonical correlation analysis
  • Basic View
  • Metadata View
  • XML View
TitleReal-time data driven deformation using kernel canonical correlation analysis
 
AuthorsFeng, WW1
Kim, BU1
Yu, Y1
 
KeywordsAnimation
Poisson Equation
Regression
Skinning
 
Issue Date2008
 
CitationSiggraph'08: International Conference On Computer Graphics And Interactive Techniques, Acm Siggraph 2008 Papers 2008, 2008 [How to Cite?]
 
AbstractAchieving intuitive control of animated surface deformation while observing a specific style is an important but challenging task in computer graphics. Solutions to this task can find many applications in data-driven skin animation, computer puppetry, and computer games. In this paper, we present an intuitive and powerful animation interface to simultaneously control the deformation of a large number of local regions on a deformable surface with a minimal number of control points. Our method learns suitable deformation subspaces from training examples, and generate new deformations on the fly according to the movements of the control points. Our contributions include a novel deformation regression method based on kernel Canonical Correlation Analysis (CCA) and a Poisson-based translation solving technique for easy and fast deformation control based on examples. Our run-time algorithm can be implemented on GPUs and can achieve a few hundred frames per second even for large datasets with hundreds of training examples. © 2008 ACM.
 
ReferencesReferences in Scopus
 
DC FieldValue
dc.contributor.authorFeng, WW
 
dc.contributor.authorKim, BU
 
dc.contributor.authorYu, Y
 
dc.date.accessioned2012-06-26T06:31:12Z
 
dc.date.available2012-06-26T06:31:12Z
 
dc.date.issued2008
 
dc.description.abstractAchieving intuitive control of animated surface deformation while observing a specific style is an important but challenging task in computer graphics. Solutions to this task can find many applications in data-driven skin animation, computer puppetry, and computer games. In this paper, we present an intuitive and powerful animation interface to simultaneously control the deformation of a large number of local regions on a deformable surface with a minimal number of control points. Our method learns suitable deformation subspaces from training examples, and generate new deformations on the fly according to the movements of the control points. Our contributions include a novel deformation regression method based on kernel Canonical Correlation Analysis (CCA) and a Poisson-based translation solving technique for easy and fast deformation control based on examples. Our run-time algorithm can be implemented on GPUs and can achieve a few hundred frames per second even for large datasets with hundreds of training examples. © 2008 ACM.
 
dc.description.naturelink_to_subscribed_fulltext
 
dc.identifier.citationSiggraph'08: International Conference On Computer Graphics And Interactive Techniques, Acm Siggraph 2008 Papers 2008, 2008 [How to Cite?]
 
dc.identifier.scopuseid_2-s2.0-57649110690
 
dc.identifier.urihttp://hdl.handle.net/10722/151936
 
dc.languageeng
 
dc.relation.ispartofSIGGRAPH'08: International Conference on Computer Graphics and Interactive Techniques, ACM SIGGRAPH 2008 Papers 2008
 
dc.relation.referencesReferences in Scopus
 
dc.subjectAnimation
 
dc.subjectPoisson Equation
 
dc.subjectRegression
 
dc.subjectSkinning
 
dc.titleReal-time data driven deformation using kernel canonical correlation analysis
 
dc.typeConference_Paper
 
<?xml encoding="utf-8" version="1.0"?>
<item><contributor.author>Feng, WW</contributor.author>
<contributor.author>Kim, BU</contributor.author>
<contributor.author>Yu, Y</contributor.author>
<date.accessioned>2012-06-26T06:31:12Z</date.accessioned>
<date.available>2012-06-26T06:31:12Z</date.available>
<date.issued>2008</date.issued>
<identifier.citation>Siggraph&apos;08: International Conference On Computer Graphics And Interactive Techniques, Acm Siggraph 2008 Papers 2008, 2008</identifier.citation>
<identifier.uri>http://hdl.handle.net/10722/151936</identifier.uri>
<description.abstract>Achieving intuitive control of animated surface deformation while observing a specific style is an important but challenging task in computer graphics. Solutions to this task can find many applications in data-driven skin animation, computer puppetry, and computer games. In this paper, we present an intuitive and powerful animation interface to simultaneously control the deformation of a large number of local regions on a deformable surface with a minimal number of control points. Our method learns suitable deformation subspaces from training examples, and generate new deformations on the fly according to the movements of the control points. Our contributions include a novel deformation regression method based on kernel Canonical Correlation Analysis (CCA) and a Poisson-based translation solving technique for easy and fast deformation control based on examples. Our run-time algorithm can be implemented on GPUs and can achieve a few hundred frames per second even for large datasets with hundreds of training examples. &#169; 2008 ACM.</description.abstract>
<language>eng</language>
<relation.ispartof>SIGGRAPH&apos;08: International Conference on Computer Graphics and Interactive Techniques, ACM SIGGRAPH 2008 Papers 2008</relation.ispartof>
<subject>Animation</subject>
<subject>Poisson Equation</subject>
<subject>Regression</subject>
<subject>Skinning</subject>
<title>Real-time data driven deformation using kernel canonical correlation analysis</title>
<type>Conference_Paper</type>
<description.nature>link_to_subscribed_fulltext</description.nature>
<identifier.scopus>eid_2-s2.0-57649110690</identifier.scopus>
<relation.references>http://www.scopus.com/mlt/select.url?eid=2-s2.0-57649110690&amp;selection=ref&amp;src=s&amp;origin=recordpage</relation.references>
</item>
Author Affiliations
  1. University of Illinois at Urbana-Champaign