Facial animation retargeting framework using radial basis functions

In this paper we demonstrate our framework of facial motion retargeting. We define pairs of source and target expressions and their variable configurations. For a given new source expression the target variables are au-tomatically adjusted accordingly. We use Radial Basis Function (RBF) based regression methods to define the relationship between source and target configurations. We also investigate both realtime use with markerless cap-ture data from web cameras, and high quality methods for production environments based on professional motion capture systems. We show that the method can handle a wide range of animation parameter types including skin-ning, blend shapes and material properties