Realistic Face Modeling by Registration of a 3-D Mesh Model and MultiView Color Images

Realistic 3-D face modeling is a challenging research topic that involves tight integration of computer vision and computer graphics techniques. Acquisition of surface textures is an indispensable step in realistic 3-D face modeling. In this paper, we propose a camera-calibration based method to register 3-D mesh models with multi-view color images. Then a global texture map is synthesized from texture patches corresponding to each image. A main difficulty here is that the texture-mapping parameters are sensitive to initially selected correspondences between the mesh model and images. To solve this problem, we developed an iterative optimization algorithm for the parameter estimation through automatic adjustment of the selected correspondences. Experimental results are given to demonstrate the performance of our method.

[1]  Kuo-Young Cheng,et al.  An automatic construction of a person's face model from the person's two orthogonal views , 2002, Geometric Modeling and Processing. Theory and Applications. GMP 2002. Proceedings.

[2]  David Salesin,et al.  Synthesizing realistic facial expressions from photographs , 1998, SIGGRAPH.

[3]  Matthew Turk,et al.  A Morphable Model For The Synthesis Of 3D Faces , 1999, SIGGRAPH.

[4]  Michael Jones,et al.  Appearance-Based Structure from Motion Using Linear Classes of 3-D Models , 2002, International Journal of Computer Vision.

[5]  Paul E. Debevec,et al.  Acquiring the reflectance field of a human face , 2000, SIGGRAPH.

[6]  Gérard G. Medioni,et al.  Generation of a 3-D face model from one camera , 2002, Object recognition supported by user interaction for service robots.

[7]  S. P. Mudur,et al.  Three-dimensional computer vision: a geometric viewpoint , 1993 .

[8]  Nicholas Ayache,et al.  3D-2D Projective Registration of Free-Form Curves and Surfaces , 1997, Comput. Vis. Image Underst..

[9]  Pascal Fua,et al.  Using model-driven bundle-adjustment to model heads from raw video sequences , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[10]  H. Seidel,et al.  Texturing Faces , 2002, Graphics Interface.