Semantic Parametric Reshaping of Human
Body Models
Yipin Yang, Yao
Yu, Yu Zhou, Sidan Du, James Davis, Ruigang Yang
We develop a novel approach to
generate human body models in a variety of shapes and poses via tuning
semantic
parameters. Our approach is
investigated with datasets of up to 3000 scanned body models which have
been
placed
in point to point correspondence.
Correspondence is established by nonrigid deformation of a template
mesh. The
large dataset allows a local model
to be learned robustly, in which individual parts of the human body can
be
accurately reshaped according to
semantic parameters. We evaluate performance on two datasets and find
that our
model outperforms existing
methods.
Citation
If you use this dataset, please cite the
following paper:
Dataset
The dataset contains about 1500 registered
male and female meshes with point-to-point correspondences
respectively.
Each mesh has 12500 vertices and 25000
facets.
The data is derived from the CAESAR dataset. I was given permission to share research results, but not original data. Thus there are no raw scans or weights, heights, etc available with our meshes.
No commercial usage of the data is allowed.
Click here
to obtain a username and password for dataset access.
Other human body data
- SCAPE - (paper website) (data) - The correspondence between the meshes above is identical to that in SCAPE
- FAUST - (website-data-code) - different people in different poses
- BodyLabs - (web) - Company commercializing body model tools
- MPI - (website-data-code) - different people in different poses from a different MPI lab
- MPII Human Shape (website-data-code) - CAESAE dataset processed by MPI
- CAESAR - (website-data) - Sells complete CAESAR dataset with more measurements and authorized to provide commercial license.
- other - (web) - Other data I find around my lab that might be helpful to someone