A Robust and Fast Face Modeling System

In this paper, we describe our face modeling system which allows a user, with a PC and an ordinary video camera, to construct their own 3D face models with minimal manual work. Furthermore, the constructed face model can be animated right away. There are two technical innovations that make our system possible. The first is a robust head motion estimation algorithm that takes advantage of physical properties of the face feature points obtained from manual marking to reduce the number of unknowns. The second innovation is to fit a set of face metrics (3D deformation vectors) to the reconstructed 3D points and markers to generate a complete face geometry. We have done live demonstrations many times and constructed 3D faces for hundreds of people. The system has proven to be robust, fast, and easy to use.

[1]  Michael Cohen,et al.  Rapid modeling of animated faces from video images , 2000, ACM Multimedia.

[2]  Keith Waters,et al.  Computer facial animation , 1996 .

[3]  Thomas Vetter,et al.  A morphable model for the synthesis of 3D faces , 1999, SIGGRAPH.

[4]  O. Faugeras.  Three-dimensional computer vision: a geometric viewpoint , 1993 .

[5]  Tomaso A. Poggio,et al.  Linear Object Classes and Image Synthesis From a Single Example Image , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Zicheng Liu,et al.  Rapid modeling of animated faces from video , 2001, Comput. Animat. Virtual Worlds.

[7]  Zicheng Liu,et al.  Model-based bundle adjustment with application to face modeling , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[8]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[9]  Zhengyou Zhang,et al.  Flexible camera calibration by viewing a plane from unknown orientations , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[10]  Takeshi Shakunaga,et al.  Integration of eigentemplate and structure matching for automatic facial feature detection , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.