Details
| Original language | English |
|---|---|
| Pages (from-to) | 337-346 |
| Number of pages | 10 |
| Journal | Computer graphics forum |
| Volume | 28 |
| Issue number | 2 |
| Publication status | Published - 27 Mar 2009 |
Abstract
Generation 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.
ASJC Scopus subject areas
- Computer Science(all)
- Computer Graphics and Computer-Aided Design
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Computer graphics forum, Vol. 28, No. 2, 27.03.2009, p. 337-346.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - A statistical model of human pose and body shape
AU - Hasler, Nils
AU - Stoll, Carsten
AU - Sunkel, M.
AU - Rosenhahn, Bodo
AU - Seidel, Hans Peter
PY - 2009/3/27
Y1 - 2009/3/27
N2 - Generation 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.
AB - Generation 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.
UR - http://www.scopus.com/inward/record.url?scp=63049140169&partnerID=8YFLogxK
U2 - 10.1111/j.1467-8659.2009.01373.x
DO - 10.1111/j.1467-8659.2009.01373.x
M3 - Article
AN - SCOPUS:63049140169
VL - 28
SP - 337
EP - 346
JO - Computer graphics forum
JF - Computer graphics forum
SN - 0167-7055
IS - 2
ER -