Optimal UV spaces for facial morphable model construction

Establishing inter-mesh dense correspondence is a key step in the process of constructing Morphable Models. The most successful approaches to date reduce this 3D correspondence problem to a 2D image morphing one by applying an interpolant in UV space - a space in which the manifold of the face is flattened into a contiguous 2D atlas. Contiguous UV spaces are natural products of the laser scanning devices popular for use in Morphable Model construction, but a wide gamut of devices can now be used to capture 3D data that do not yield a UV space representation conducive to warping. In this paper we explore how to optimally construct contiguous UV spaces from both annotated and non-annotated facial meshes with efficient cylindrical and spherical projection operations.

[1]  Alla Sheffer,et al.  Cross-parameterization and compatible remeshing of 3D models , 2004, ACM Trans. Graph..

[2]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.

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

[4]  I. D. Coope,et al.  Circle fitting by linear and nonlinear least squares , 1993 .

[5]  Peter Schröder,et al.  Consistent mesh parameterizations , 2001, SIGGRAPH.

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

[7]  William A. P. Smith,et al.  3D morphable face models revisited , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Andrew S. Glassner,et al.  Proceedings of the 27th annual conference on Computer graphics and interactive techniques , 1994, SIGGRAPH 1994.

[9]  Adrian Hilton,et al.  A FACS valid 3D dynamic action unit database with applications to 3D dynamic morphable facial modeling , 2011, 2011 International Conference on Computer Vision.

[10]  Lijun Yin,et al.  A high-resolution 3D dynamic facial expression database , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[11]  Stefanos Zafeiriou,et al.  Bayesian Active Appearance Models , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Vladislav Kraevoy,et al.  Cross-parameterization and compatible remeshing of 3D models , 2004, SIGGRAPH 2004.

[13]  Marc Alexa,et al.  Merging polyhedral shapes with scattered features , 1999, Proceedings Shape Modeling International '99. International Conference on Shape Modeling and Applications.