In this paper, we demonstrate a system for synthesizing high-resolution, realistic 3D human body shapes according to user-specified anthropometric parameters. We begin with a corpus of whole-body 3D laser range scans of 250 different people. For each scan, we warp a common template mesh to fit each scanned shape, thereby creating a one-to-one vertex correspondence between each of the example body shapes. Once we have a common surface representation for each example, we then use principal component analysis to reduce the data storage requirements. The final step is to relate the variation of body shape with concrete parameters, such as body circumferences, point-to-point measurements, etc. These parameters can then be used as "sliders" to synthesize new individuals with the required attributes, or to edit the attributes of scanned individuals.
[1]
Thomas Vetter,et al.
A morphable model for the synthesis of 3D faces
,
1999,
SIGGRAPH.
[2]
Nadia Magnenat-Thalmann,et al.
An automatic modeling of human bodies from sizing parameters
,
2003,
I3D '03.
[3]
Zoran Popovic,et al.
The space of human body shapes: reconstruction and parameterization from range scans
,
2003,
ACM Trans. Graph..
[4]
Matthew Stone,et al.
An anthropometric face model using variational techniques
,
1998,
SIGGRAPH.
[5]
M. Turk,et al.
Eigenfaces for Recognition
,
1991,
Journal of Cognitive Neuroscience.
[6]
Zoran Popovic,et al.
Articulated body deformation from range scan data
,
2002,
SIGGRAPH.