A Statistical Model of Human Pose and Body Shape


Synthetic human shapes play an important part in the media industry. Realistic human animations are essential in many projects in the movie industry as well as in computer gaming. Automatic generation of diverse crowds is one of the disciplines that have to be solved to allow movies or games to feature ever larger crowds.

The aim of this research is to develop a detailed statistical model of human body shapes by leveraging an encoding for mesh surfaces that is linear with respect to rotations and scalings and describes human pose and body shape in a unified framework. We have captured 114 subjects in a subset of 35 poses using a 3D laser scanner. Additionally, we measured body weight and several other biometric measures of the subject. Nonrigid registration is performed to bring the scans into correspondence. The following 3D viewer shows the subjects in the rest pose that was captured for all subjects.

[drag to rotate]


N. Hasler, T. Thormählen, B. Rosenhahn, H.-P. Seidel: Learning Skeletons for Shape and Pose, ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (I3D 2010), Washington DC, USA, February 2010. (PDF)
N. Hasler, C. Stoll, M. Sunkel, B. Rosenhahn, H.-P. Seidel: A Statistical Model of Human Pose and Body Shape, Computer Graphics Forum (Proc. Eurographics 2009), Munich, Germany, March 2009. (PDF)
N. Hasler, C. Stoll, B. Rosenhahn, T. Thormählen, H.-P. Seidel: Estimating Body Shape of Dressed Humans, Shape Modeling International (SMI 2009), Beijing, China, June 2009. (PDF)

Source Code

Matlab source code for encoding and decoding the relative rotation encoding that is at the heart of the proposed model is available here.

Public Data

On request, we make all 3D scans, the registered scans, and the PCA model available for scientific purposes. To obtain a copy, please send an email gvvperfcapeva@mpi-inf.mpg.de, with further information about you and your work. Please understand that we can only provide the data to you if you are a senior project manager or senior researcher at your institution.

We would also like to ask you to acknowledge the origin of the data by citing the above Eurographics paper in any publication using the 3D scans or source code.

Please note that you are not allowed to pass the data to a third party without prior permission.


For questions and comments contact the gvvperfcapeva Team