From synthesis to analysis: fitting human animation models to image data

We show that we can effectively fit complex animation models to noisy image data. Our approach is based on robust least squares adjustment and takes advantage of three complementary sources of information: stereo data, silhouette edges and 2D feature points. We take stereo to be our main information source and use the other two whenever available. In this way, complete head models-including ears and hair-can be acquired with a cheap and entirely passive sensor, such as an ordinary video camera. The motion parameters of limbs can be similarly captured. They can then be fed to existing animation software to produce synthetic sequences.

[1]  Thierry Viéville,et al.  Canonical Representations for the Geometries of Multiple Projective Views , 1996, Comput. Vis. Image Underst..

[2]  Andrew Zisserman,et al.  Resolving ambiguities in auto–calibration , 1998, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[3]  Wei Sun,et al.  Virtual people: capturing human models to populate virtual worlds , 1999, Proceedings Computer Animation 1999.

[4]  D. Gennery,et al.  Calibration and Orientation of Cameras in Computer Vision , 2001 .

[5]  Horst A. Beyer,et al.  System Calibration Through Self-Calibration , 2001 .

[6]  WON-SOOK LEE,et al.  From Real Faces To Virtual Faces : Problems and Solutions , 1999 .

[7]  Ioannis A. Kakadiaris,et al.  Active part-decomposition, shape and motion estimation of articulated objects: a physics-based approach , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Daniel Thalmann,et al.  Interactive Shape Design Using Metaballs and Splines , 1995 .

[9]  Demetri Terzopoulos,et al.  Realistic modeling for facial animation , 1995, SIGGRAPH.

[10]  Daniel Thalmann,et al.  Fast realistic human body deformations for animation and VR applications , 1996, Proceedings of CG International '96.

[11]  Peter F. Sturm,et al.  Critical motion sequences for monocular self-calibration and uncalibrated Euclidean reconstruction , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  P. Fua.  From Multiple Stereo Views to Multiple 3-D Surfaces , 2022 .

[13]  Daniel Thalmann,et al.  Simulation of Facial Muscle Actions Based on Rational Free Form Deformations , 1992, Comput. Graph. Forum.

[14]  Dimitris N. Metaxas,et al.  Deformable model-based shape and motion analysis from images using motion residual error , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[15]  Pascal Fua,et al.  From Regular Images to Animated Heads: A Least Squares Approach , 1998, ECCV.