3D facial modeling for animation: A nonlinear approach

This paper presents an efficient nonlinear method for 3D facial modeling from a single image, with the support of 3D face examples. First a set of feature points is extracted from the image. The feature points are then used to automatically estimate the head pose parameters using the 3D mean face in our database as a reference model. After the pose recovery, a similarity measurement function is proposed to find the neighborhood for the given image. The scope of neighborhood can be determined adaptively using our cross-validation algorithm. Furthermore, the individual 3D shape is synthesized by neighborhood interpolation. Texture mapping is achieved based on feature points. The experimental results show that our algorithm can robustly produce 3D facial models from images captured in various scenarios.