Modeling of Human Faces with Parameterized Local Shape Morphing

This paper presents an automatic runtime system for generating varied realistic geometric models of human faces based on morphing of facial features. Our method takes as examples 3D scanned human face models in order to exploit the parameter-to-geometry correlations that are presented in the real faces. In order to establish correspondence among models, we use a two-step model fitting approach to conform a generic model onto each scanned data. We transform the obtained data sets of facial feature shapes into vector space representations by applying a principal component analysis (PCA). Using the PCA coefficients as a compact shape representation, we approach the shape synthesis problem by forming scattered data interpolation functions that are devoted to the generation of desired shape by taking the anthropometric parameters as input. At runtime, the interpolation functions are evaluated at the input parameter values to produce new face geometries at an interactive rate