The Stitched Puppet (SP) is a realistic part-based 3D body model of the human body.

It offers the best features of part-based body models used in Computer Vision and statistical body models used in Computer Graphics.

In SP the human body is represented by a set of independent meshes, one for each body part. This representation maps to a graphical model in which nodes of the graph correspond to body parts that can independently translate and rotate in 3D. Body parts deform according to learned deformation models to represent different body shapes and to capture pose-dependent shape variations, while pairwise potentials define a "stitching cost" for pulling the limbs apart.

Unlike existing realistic 3D body models, the distributed representation facilitates inference by allowing the model to more effectively explore the space of poses. We infer pose and body shape using a form of particle-based max-product belief propagation; this gives SP the computational advantages of part-based models with the realism of statistical 3D body models. We have applied SP to problems involving estimating human shape and pose from 3D data.

(Read the full extended abstract)

Further Information



Referencing the Model

Here are the Bibtex snippets for citing the SP Model in your work.

Main paper and benchmark:
@inproceedings{Zuffi:CVPR:2015,
  title = {The Stitched Puppet: A Graphical Model of {3D} Human Shape and Pose},
  author = {Zuffi, Silvia and Black, Michael J.},
  booktitle = { IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2015},
  month = jun,
  abstract = {We propose a new 3D model of the human body that is both realistic and part-based. The body is represented by
  a graphical model in which nodes of the graph correspond to body parts that can independently translate and rotate
  in 3D as well as deform to capture pose-dependent shape variations. Pairwise potentials define a “stitching cost” for
  pulling the limbs apart, giving rise to the stitched puppet model (SPM). Unlike existing realistic 3D body models, the
  distributed representation facilitates inference by allowing the model to more effectively explore the space of poses,
  much like existing 2D pictorial structures models. We infer pose and body shape using a form of particle-based max-product belief propagation. This gives the SPM the realism of recent 3D body models with the computational advantages
  of part-based models. We apply the SPM to two challenging problems involving estimating human shape and
  pose from 3D data. The first is the FAUST mesh alignment challenge (http://faust.is.tue.mpg.de/), where ours is the first method to successfully align all 3D meshes. The second involves estimating pose and shape from crude visual hull representations of complex
  body movements.},
  year = {2015}
}