Similar articles

Abstract: Driving facial animation based on tens of tracked markers is a challenging task due to the complex topology and to the non-rigid nature of human faces. We propose a solution named manifold bayesian regression. First a novel distance metric, the geodesic manifold distance, is introduced to replace the Euclidean distance. The problem of facial animation can be formulated as a sparse warping kernels regression problem, in which the geodesic manifold distance is used for modelling the topology and discontinuities of the face models. The geodesic manifold distance can be adopted in traditional regression methods, e.g. radial basis functions without much tuning. We put facial animation into the framework of bayesian regression. Bayesian approaches provide an elegant way of dealing with noise and uncertainty. After the covariance matrix is properly modulated, Hybrid Monte Carlo is used to approximate the integration of probabilities and get deformation results. The experimental results showed that our algorithm can robustly produce facial animation with large motions and complex face models.

[1] Blanz, V., Basso, C., Poggio, T., Vetter, T., 2003. Reanimating Faces in Images and Video. Computer Graphics Forum, EUROGRAPHICS 2003, Granada, Spain, 22(3):641-650.

[2] Cutler, R., Rui, Y., Gupta, A., Cadiz, J., Tashev, I., He, L.W., Colburn, A., Zhang, Z.Y., Liu, Z.C., Silverberg, S., 2002. Distributed Meetings: A Meeting Capture and Broadcasting System. Proc. of ACM Mulitmedia 2002, Juan-les-Pins, France.

[3] Duane, S., Kennedy, A.D., Pendleton, B.J., Roweth, D., 1987. Hybrid Monte Carlo. Physics Letters B, 195(2):216-222.

[4] Guenter, B., Grimm, C., Wood, D., Malvar, H., Pighin, F., 1998. Making Faces. SIGGRAPH 98 Proceedings, p.55-66.

[5] Hertzmann, A., 2003. Machine Learning for Computer Graphics: A Manifesto and Tutorial. Proceeding of Pacific Graphics 2003, Banff, Alberta, p.22-36.

[6] Huang, X.S., Li, S.Z., Wang, Y.S., 2004. Learning with Cascade for Classification of Non-Convex Manifolds. First IEEE Workshop on Face Processing in Video, Washington, D.C., USA.

[7] Joshi, P., Tien, W.C., 2003. Learning Controls for Blend Shape Based Realistic Facial Animation. Proceedings of EUROGRAPHICS03, p.187-192.

[8] Lee, S., Wolberg, G., Shin, S.Y., 1997. Scattered data interpolation with multilevel B-splines. IEEE Transactions on Visualization and Computer Graphics. 3(3):228-244.

[9] Liu, X., Zhuang, Y.T., Pan, Y.H., 1999. Video Based Human Animation Technique. ACM Multimedia99, Orlando, Florida, USA, p.353-362.

[10] MacKay, D.J.C., 1998. Introduction to Gaussian Processes. In: Bishop, C.M.(Ed.), Neural Networks and Machine Learning. Kluwer Academic Press, p.133-166.

[11] Na, K., Jung, M., 2004. Hierarchical Retargeting of Fine Facial Motions. Proceedings of EUROGRAPHICS04, 687-695.

[12] Niyogi, P., Belkin, M., 2002. Laplacian Eigenmaps for Dimensionality Reduction and Data Representation. Technical Report, University of Chicago.

[13] Noh, J., Neumann, U., 2001. Expression Cloning. Proceeding of SIGGRAPH01, p.271-288.

[14] Noh, J., Fidaleo, D., Neumann, U., 2000. Animated Deformations with Radial Basis Functions. Proceedings of the ACM Symposium on Virtual Reality Software and Technology (VRST), p.166-174.

[15] Pan, Y.H., Zhuang, Y.T., Liu, X.M., 2000. Video motion capture in VBA—video-based animation. Journal of Zhejiang University SCIENCE, 1(1):1-7.

[16] Pyun, H., Kim, Y., Chae, W., Kang, H.Y., Shin, S.Y., 2003. An Example-Based Approach for Facial Expression Cloning. ACM SIGGRAPH/Eurographics Symposium on Computer Animation, p.167-176.

[17] Roweis, S., Saul, L., 2000. Nonlinear dimensionality reduction by locally linear embedding. Science, 290(5500):2323-2326.

[18] Sánchez Lorenzo, M.A., Edge, J.D., King, S.A., Maddock, S.C., 2003. Use and Re-use of Facial Motion Capture Data. Vision, Video, and Graphics, VVG 2003. University of Bath, UK, p.135-142.

[19] Tenenbaum, J.B., de Silva, V., Langford, J.C., 2000. A global geometric framework for nonlinear dimensionality reduction. Science, 290(5500):2319-2323.

[20] Williams, L., 1990. Performance-Driven Facial Animation. SIGGRAPH 90 Proceedings, p.235-242.

[21] Williams, C.K.I., Rasmussen, C.E., 1996. Gaussian Processes for Regression. Proceeding of NIPS 8, MIT Press.

[22] Zhang, J.P., Li, S.Z., Wang, J., 2004. Manifold Learning and Applications in Recognition. In: Tan, Y.P., Yap, K.H., Wang, L.P.(Eds.), Intelligent Multimedia Processing with Soft Computing. Springer-Verlag, Heidelberg.

[23] Zhuang, Y.T., Liu, X.M., Pan, Y.H., 1999. Video Motion Capture Using Feature Tracking and Skeleton Reconstruction. IEEE International Conference on Image Processing (ICIP’99), Kobe, Japan, p.232-236.