Abstract
In this paper, we propose a framework to customize a face model for reusing animation. In this framework, two orthogonal photos of a human face are used as input. Based on them, a set of feature points is manually selected. Then, the existing face model will be adapted for both the geometry and muscle model underneath. We formulate it as a non-linear optimization problem and apply the Levenberg-Marquardt method for the solution. We can get the result instantly. The result is a new animation-ready model with the same look as the two photos. Applying the previous motion specification to this model, we can reuse the animation. Our initial results demonstrate that our approach is effective. The main technique features of our method are: (a) we formulate the reconstruction as a non-linear optimization problem and solve it using the Levenberg-Marquardt method; (b) we adapt a uniform framework that integrates the muscle models and the facemask; and (c) we employ the Simple2.0, a generic animation-ready face model free available on the Internet [Wate87, Wate98], to perform the face model customization and animation.