3D morphable face models revisited

In this paper we revisit the process of constructing a high resolution 3D morphable model of face shape variation. We demonstrate how the statistical tools of thin-plate splines and Procrustes analysis can be used to construct a morphable model that is both more efficient and generalises to novel face surfaces more accurately than previous models. We also reformulate the probabilistic prior that the model provides on the distribution of parameter vector lengths. This distribution is determined solely by the number of model dimensions and can be used as a regularisation constraint in fitting the model to data without the need to empirically choose a parameter controlling the trade off between plausibility and quality of fit. As an example application of this improved model, we show how it may be fitted to a sparse set of 2D feature points (approximately 100). This provides a rapid means to estimate high resolution 3D face shape for a face in any pose given only a single face image. We present experimental results using ground truth data and hence provide absolute reconstruction errors. On average, the per vertex error of the reconstructed faces is less than 3.6 mm.

[1]  Athinodoros S. Georghiades,et al.  Recovering 3-D Shape and Reflectance From a Small Number of Photographs , 2003, Rendering Techniques.

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

[3]  Sami Romdhani,et al.  Combining PCA and LFA for Surface Reconstruction from a Sparse Set of Control Points , 2006, 7th International Conference on Automatic Face and Gesture Recognition (FGR06).

[4]  K. Mardia,et al.  Statistical Shape Analysis , 1998 .

[5]  P. Jonathon Phillips,et al.  Face recognition based on frontal views generated from non-frontal images , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[6]  Fred L. Bookstein,et al.  Landmark methods for forms without landmarks: morphometrics of group differences in outline shape , 1997, Medical Image Anal..

[7]  T. Vetter,et al.  A statistical method for robust 3D surface reconstruction from sparse data , 2004 .

[8]  R. Basri,et al.  Statistical Symmetric Shape from Shading for 3D Structure Recovery of Faces , 2004, eccv 2004.

[9]  David J. Kriegman,et al.  Face Recognition Using 3-D Models: Pose and Illumination , 2006, Proceedings of the IEEE.

[10]  Sami Romdhani,et al.  Estimating 3D shape and texture using pixel intensity, edges, specular highlights, texture constraints and a prior , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[11]  Raghu Machiraju,et al.  Model-based 3D face capture with shape-from-silhouettes , 2003, 2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443).

[12]  Fred L. Bookstein,et al.  Principal Warps: Thin-Plate Splines and the Decomposition of Deformations , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  David J. Kriegman,et al.  From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Berthold K. P. Horn,et al.  Closed-form solution of absolute orientation using unit quaternions , 1987 .

[15]  Alexander M. Bronstein,et al.  Three-Dimensional Face Recognition , 2005, International Journal of Computer Vision.

[16]  Thomas Vetter,et al.  Face Recognition Based on Fitting a 3D Morphable Model , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Lei Zhang,et al.  Face recognition from a single training image under arbitrary unknown lighting using spherical harmonics , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.