A Statistical Model of Human Pose and Body Shape

Simple item page
dc.contributor.authorHasler, N.en_US
dc.contributor.authorStoll, C.en_US
dc.contributor.authorSunkel, M.en_US
dc.contributor.authorRosenhahn, B.en_US
dc.contributor.authorSeidel, H.-P.en_US
dc.date.accessioned2015-02-23T10:15:34Z
dc.date.available2015-02-23T10:15:34Z
dc.date.issued2009en_US
dc.description.abstractGeneration and animation of realistic humans is an essential part of many projects in today s media industry. Especially, the games and special effects industry heavily depend on realistic human animation. In this work a unified model that describes both, human pose and body shape is introduced which allows us to accurately model muscle deformations not only as a function of pose but also dependent on the physique of the subject. Coupled with the model s ability to generate arbitrary human body shapes, it severely simplifies the generation of highly realistic character animations. A learning based approach is trained on approximately 550 full body 3D laser scans taken of 114 subjects. Scan registration is performed using a non-rigid deformation technique. Then, a rotation invariant encoding of the acquired exemplars permits the computation of a statistical model that simultaneously encodes pose and body shape. Finally, morphing or generating meshes according to several constraints simultaneously can be achieved by training semantically meaningful regressors.en_US
dc.description.number2en_US
dc.description.seriesinformationComputer Graphics Forumen_US
dc.description.volume28en_US
dc.identifier.doi10.1111/j.1467-8659.2009.01373.xen_US
dc.identifier.issn1467-8659en_US
dc.identifier.pages337-346en_US
dc.identifier.urihttps://doi.org/10.1111/j.1467-8659.2009.01373.xen_US
dc.publisherThe Eurographics Association and Blackwell Publishing Ltden_US
dc.titleA Statistical Model of Human Pose and Body Shapeen_US
Files
Collections
28-Issue 2
Full Papers 2009 - CGF 28-Issue 2