 |
Center for Nonlinear Studies |
Directly sensing the shape and motion of people would enable many new applications. Unfortunately no such sensor yet exists. We hypothesize that a high quality surface prior model of human shape will be sufficient to enable sensing using todays inadequate sensors. We introduce a data-driven method for building a human shape model that spans variation in both subject shape and pose. The method is based on a representation that incorporates both articulated and nonrigid deformations. We learn a pose deformation model that derives the nonrigid surface deformation as a function of the pose of the articulated skeleton. We also learn a separate model of variation based on body shape. Our two models can becombined to produce 3D surface models with realistic muscle deformation for different people in different poses, when neither appear in the training set. We show how the model can be used for shape completion --- generating a complete surface mesh given a limited set of markers specifying the target shape. We present applications of shape completion to partial view completion and motion capture animation. In particular, our method is capable of constructing a high-quality animated surface model of a moving person, with realistic muscle deformation, using just a single static scan of that person. We also show results using this model to recover shape and motion from traditional cameras.
Host: Sriram Swaninarayan