Real-Time Synthesis of 3D Animations by Learning Parametric Gaussians Using Self-Organizing Mixture Networks

  • Yi Wang
  • Hujun Yin
  • Li-Zhu Zhou
  • Zhi-Qiang Liu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4233)


In this paper, we present a novel real-time approach to synthesizing 3D character animations of required style by adjusting a few parameters or scratching mouse cursor. Our approach regards learning captured 3D human motions as parametric Gaussians by the self-organizing mixture network (SOMN). The learned model describes motions under the control of a vector variable called the style variable, and acts as a probabilistic mapping from the low-dimensional style values to high-dimensional 3D poses. We have designed a pose synthesis algorithm and developed a user friendly graphical interface to allow the users, especially animators, to easily generate poses by giving style values. We have also designed a style-interpolation method, which accepts a sparse sequence of key style values and interpolates it and generates a dense sequence of style values for synthesizing a segment of animation. This key-styling method is able to produce animations that are more realistic and natural-looking than those synthesized by the traditional key-framing technique.


Mixture Model Style Variable Motion Synthesis Character Animation User Friendly Graphical Interface 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Li, Y., Wang, T., Shum, H.Y.: Motion texture: A two-level statistical model for character motion synthesis. In: Proc. ACM SIGGRAPH, pp. 465–472 (2002)Google Scholar
  2. 2.
    Grochow, K., Martin, S.L., Hertzmann, A., Popović, Z.: Style-based inverse kinematics. In: Proc. ACM SIGGRAPH, pp. 522–531 (2004)Google Scholar
  3. 3.
    Brand, M., Hertzmann, A.: Style machines. In: Proc. ACM SIGGRAPH, pp. 183–192 (2000)Google Scholar
  4. 4.
    Ostendorf, M., Digalakis, V.V., Kimball, O.A.: From HMM’s to segment models: a unified view of stochastic modeling for speech recognition. IEEE Transactions on Speech and Audio Processing 4(5), 360–378 (1996)CrossRefGoogle Scholar
  5. 5.
    Gales, M., Young, S.: The theory of segmental hidden Markov models. Technical report, Cambridge Univ. Eng. Dept (1993)Google Scholar
  6. 6.
    Lawrence, N.D.: Gaussian process latent variable models for visualisation of high dimensional data. In: Proc. 16th NIPS (2004)Google Scholar
  7. 7.
    Wilson, A.D., Bobick, A.: Parametric hidden markov models for gesture recognition. IEEE Trans. Pattern Analysis Machine Intelligence 21(9), 884–900 (1999)CrossRefGoogle Scholar
  8. 8.
    Brand, M.: Pattern discovery via entropy minimization. In: Heckerman, D., Whittaker, C. (eds.) Artificial Intelligence and Statistics, vol. 7, Morgan Kaufmann, Los Altos (1999)Google Scholar
  9. 9.
    Yin, H., Allinson, N.M.: Self-organizing mixture networks for probability density estimation. IEEE Trans. Neural Networks 12, 405–411 (2001)CrossRefGoogle Scholar
  10. 10.
    Ormoneit, D., Tresp, V.: Averaging, maximum penalised likelihood and bayesian estimation for improving gaussian mixture probability density estimates. IEEE Trans. Neural Networks 9, 639–650 (1998)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Yi Wang
    • 1
  • Hujun Yin
    • 2
  • Li-Zhu Zhou
    • 1
  • Zhi-Qiang Liu
    • 3
  1. 1.Department of Computer Science and TechnologyTsinghua University, Graduate School at ShenzhenChina
  2. 2.School of Electrical and Electronic EngineeringThe University of ManchesterUK
  3. 3.School of Creative MediaCity University of Hong KongKowloonHong Kong

Personalised recommendations