File Download
 
Links for fulltext
(May Require Subscription)
 
Supplementary

Conference Paper: Controllable hand deformation from sparse examples with rich details
  • Basic View
  • Metadata View
  • XML View
TitleControllable hand deformation from sparse examples with rich details
 
AuthorsHuang, H1
Zhao, L4
Yin, K
Qi, Y4
Yu, Y2
Tong, X1
 
KeywordsControl point
Data-driven model
Deformation models
Digital model
Fine feature
 
Issue Date2011
 
PublisherAssociation for Computing Machinery, Inc.
 
CitationThe 2011 ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA 2011), Vancouver, B.C., 5-7 August 2011. In Proceedings of the SCA, 2011, p. 73-82 [How to Cite?]
DOI: http://dx.doi.org/10.1145/2019406.2019416
 
AbstractRecent advances in laser scanning technology have made it possible to faithfully scan a real object with tiny geometric details, such as pores and wrinkles. However, a faithful digital model should not only capture static details of the real counterpart but also be able to reproduce the deformed versions of such details. In this paper, we develop a data-driven model that has two components respectively accommodating smooth large-scale deformations and high-resolution deformable details. Large-scale deformations are based on a nonlinear mapping between sparse control points and bone transformations. A global mapping, however, would fail to synthesize realistic geometries from sparse examples, for highly-deformable models with a large range of motion. The key is to train a collection of mappings defined over regions locally in both the geometry and the pose space. Deformable fine-scale details are generated from a second nonlinear mapping between the control points and per-vertex displacements. We apply our modeling scheme to scanned human hand models. Experiments show that our deformation models, learned from extremely sparse training data, are effective and robust in synthesizing highly-deformable models with rich fine features, for keyframe animation as well as performance-driven animation. We also compare our results with those obtained by alternative techniques. Copyright © 2011 by the Association for Computing Machinery, Inc.
 
ISBN978-1-4503-0923-3
 
DOIhttp://dx.doi.org/10.1145/2019406.2019416
 
ReferencesReferences in Scopus
 
DC FieldValue
dc.contributor.authorHuang, H
 
dc.contributor.authorZhao, L
 
dc.contributor.authorYin, K
 
dc.contributor.authorQi, Y
 
dc.contributor.authorYu, Y
 
dc.contributor.authorTong, X
 
dc.date.accessioned2012-06-26T06:32:22Z
 
dc.date.available2012-06-26T06:32:22Z
 
dc.date.issued2011
 
dc.description.abstractRecent advances in laser scanning technology have made it possible to faithfully scan a real object with tiny geometric details, such as pores and wrinkles. However, a faithful digital model should not only capture static details of the real counterpart but also be able to reproduce the deformed versions of such details. In this paper, we develop a data-driven model that has two components respectively accommodating smooth large-scale deformations and high-resolution deformable details. Large-scale deformations are based on a nonlinear mapping between sparse control points and bone transformations. A global mapping, however, would fail to synthesize realistic geometries from sparse examples, for highly-deformable models with a large range of motion. The key is to train a collection of mappings defined over regions locally in both the geometry and the pose space. Deformable fine-scale details are generated from a second nonlinear mapping between the control points and per-vertex displacements. We apply our modeling scheme to scanned human hand models. Experiments show that our deformation models, learned from extremely sparse training data, are effective and robust in synthesizing highly-deformable models with rich fine features, for keyframe animation as well as performance-driven animation. We also compare our results with those obtained by alternative techniques. Copyright © 2011 by the Association for Computing Machinery, Inc.
 
dc.description.naturelink_to_OA_fulltext
 
dc.description.otherThe 2011 ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA 2011), Vancouver, B.C., 5-7 August 2011. In Proceedings of the SCA, 2011, p. 73-82
 
dc.identifier.citationThe 2011 ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA 2011), Vancouver, B.C., 5-7 August 2011. In Proceedings of the SCA, 2011, p. 73-82 [How to Cite?]
DOI: http://dx.doi.org/10.1145/2019406.2019416
 
dc.identifier.doihttp://dx.doi.org/10.1145/2019406.2019416
 
dc.identifier.epage82
 
dc.identifier.hkuros200761
 
dc.identifier.isbn978-1-4503-0923-3
 
dc.identifier.scopuseid_2-s2.0-80052604608
 
dc.identifier.spage73
 
dc.identifier.urihttp://hdl.handle.net/10722/152008
 
dc.languageeng
 
dc.publisherAssociation for Computing Machinery, Inc.
 
dc.publisher.placeUnited States
 
dc.relation.ispartofProceedings of the 2011 ACM SIGGRAPH/Eurographics Symposium on Computer Animation, SCA '11
 
dc.relation.referencesReferences in Scopus
 
dc.rightsProceedings of the 2011 ACM SIGGRAPH/Eurographics Symposium on Computer Animation, SCA '11. Copyright © Association for Computing Machinery, Inc.
 
dc.subjectControl point
 
dc.subjectData-driven model
 
dc.subjectDeformation models
 
dc.subjectDigital model
 
dc.subjectFine feature
 
dc.titleControllable hand deformation from sparse examples with rich details
 
dc.typeConference_Paper
 
<?xml encoding="utf-8" version="1.0"?>
<item><contributor.author>Huang, H</contributor.author>
<contributor.author>Zhao, L</contributor.author>
<contributor.author>Yin, K</contributor.author>
<contributor.author>Qi, Y</contributor.author>
<contributor.author>Yu, Y</contributor.author>
<contributor.author>Tong, X</contributor.author>
<date.accessioned>2012-06-26T06:32:22Z</date.accessioned>
<date.available>2012-06-26T06:32:22Z</date.available>
<date.issued>2011</date.issued>
<identifier.citation>The 2011 ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA 2011), Vancouver, B.C., 5-7 August 2011. In Proceedings of the SCA, 2011, p. 73-82</identifier.citation>
<identifier.isbn>978-1-4503-0923-3</identifier.isbn>
<identifier.uri>http://hdl.handle.net/10722/152008</identifier.uri>
<description.abstract>Recent advances in laser scanning technology have made it possible to faithfully scan a real object with tiny geometric details, such as pores and wrinkles. However, a faithful digital model should not only capture static details of the real counterpart but also be able to reproduce the deformed versions of such details. In this paper, we develop a data-driven model that has two components respectively accommodating smooth large-scale deformations and high-resolution deformable details. Large-scale deformations are based on a nonlinear mapping between sparse control points and bone transformations. A global mapping, however, would fail to synthesize realistic geometries from sparse examples, for highly-deformable models with a large range of motion. The key is to train a collection of mappings defined over regions locally in both the geometry and the pose space. Deformable fine-scale details are generated from a second nonlinear mapping between the control points and per-vertex displacements. We apply our modeling scheme to scanned human hand models. Experiments show that our deformation models, learned from extremely sparse training data, are effective and robust in synthesizing highly-deformable models with rich fine features, for keyframe animation as well as performance-driven animation. We also compare our results with those obtained by alternative techniques. Copyright &#169; 2011 by the Association for Computing Machinery, Inc.</description.abstract>
<language>eng</language>
<publisher>Association for Computing Machinery, Inc.</publisher>
<relation.ispartof>Proceedings of the 2011 ACM SIGGRAPH/Eurographics Symposium on Computer Animation, SCA &apos;11</relation.ispartof>
<rights>Proceedings of the 2011 ACM SIGGRAPH/Eurographics Symposium on Computer Animation, SCA &apos;11. Copyright &#169; Association for Computing Machinery, Inc.</rights>
<subject>Control point</subject>
<subject>Data-driven model</subject>
<subject>Deformation models</subject>
<subject>Digital model</subject>
<subject>Fine feature</subject>
<title>Controllable hand deformation from sparse examples with rich details</title>
<type>Conference_Paper</type>
<description.nature>link_to_OA_fulltext</description.nature>
<identifier.doi>10.1145/2019406.2019416</identifier.doi>
<identifier.scopus>eid_2-s2.0-80052604608</identifier.scopus>
<identifier.hkuros>200761</identifier.hkuros>
<relation.references>http://www.scopus.com/mlt/select.url?eid=2-s2.0-80052604608&amp;selection=ref&amp;src=s&amp;origin=recordpage</relation.references>
<identifier.spage>73</identifier.spage>
<identifier.epage>82</identifier.epage>
<publisher.place>United States</publisher.place>
<description.other>The 2011 ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA 2011), Vancouver, B.C., 5-7 August 2011. In Proceedings of the SCA, 2011, p. 73-82</description.other>
<bitstream.url>http://hub.hku.hk/bitstream/10722/152008/1/re01.htm</bitstream.url>
</item>
Author Affiliations
  1. Microsoft Research Asia
  2. University of Illinois at Urbana-Champaign
  3. National University of Singapore
  4. Beijing University of Aeronautics and Astronautics