Skip to Main Content
Construction and animation of realistic human facial models is an important research field of computer graphics. How to efficiently create an individualized facial model for animation is still a challenge. In this paper, we present a method for 3D facial model synthesis that combines the traditional free-form deformation (FFD) model with techniques of data interpolation based on Dirichlet/Voronoi diagrams. With 18 feature points extracted from 2D facial images in two orthogonal views, Dirichlet free form deformation (DFFD) is utilized for modifying a generic 3D face to produce the individual face. The main advantages of this method over former extensions of FFD is in removing the constraints on control lattice and control points location. In addition, by assigning different weights to those control points, we improve the DFFD algorithm to make it more adaptable to the facial deformation. The reconstructed 3D faces can be used to generate different facial animations.
Date of Conference: 2-5 July 2006