Matthew Brand
ABSTRACT
We approach the problem of stylistic motion synthesis by learning motion patterns from a highly varied set of motion capture sequences. Each sequence may have a distinct choreography, performed in a distinct sytle. Learning identifies common choreographic elements across sequences, the different styles in which each element is performed, and a small number of stylistic degrees of freedom which span the many variations in the dataset. The learned model can synthesize novel motion data in any interpolation or extrapolation of styles. For example, it can convert novice ballet motions into the more graceful modern dance of an expert. The model can also be driven by video, by scripts or even by noise to generate new choreography and synthesize virtual motion-capture in many styles.
- 1.L. Baum. An inequality and associated maximization technique in statistical estimation of probabilistic functions of Markov processes. Inequalities, 3:1-8, 1972.Google Scholar
- 2.M. Brand. Pattern discovery via entropy minimization. In D. Heckerman and C. Whittaker, editors, Artificial Intelligence and Statistics #7. Morgan Kaufmann., January 1999.Google Scholar
- 3.M. Brand. Exploring variational structure by cross-entropy optimization. In P. Langley, editor, P1vceedings, International Conference on Machine Learning, 2000. Google ScholarDigital Library
- 4.M. Brand. Voice puppetry. P1vceedings of SIGGRAPH 99, pages 21-28, August 1999. Google ScholarDigital Library
- 5.M. Brand. Shadow puppetry. P1vceedings oflCCV 99, September 1999. Google ScholarDigital Library
- 6.C. Bregler. Learning and recognizing human dynamics in video sequences. P1vceedings of CVPR 97, 1997. Google ScholarDigital Library
- 7.A. Bruderlin and L. Williams. Motion signal processing. P1vceedings of SIG- GRAPH 95, pages 97-104, August 1995. Google ScholarDigital Library
- 8.J. Buhmann. Empirical risk approximation: An induction principle for unsupervised leaming. Technical Report IAI-TR-98-3, Institut fiir Intbrmatik III, Universitfit Bonn. 1998., 1998. Google Scholar
- 9.R.M. Corless, G. H. Gonnet, D. E. G. Hare, D. J. Jeffrey, and D. E. Knuth. On the Lambert W function. Advances in Computational Mathematics, 5:329-359, 1996.Google ScholarCross Ref
- 10.W.T. Freeman and J. B. Tenenbaum. Learning bilinear models for two-thctor problems in vision. In P~vceedings, Conf. on Computer Vision and Pattern Recognition, pages 554-560, San Juan, PR, 1997. Google ScholarDigital Library
- 11.M. Gleicher. Motion editing with spacetime constraints. 1997 Symposium on Interactive 3D Graphics, pages 139-148, April 1997. Google ScholarDigital Library
- 12.M. Gleicher. Retargeting motion to new characters. P~vceedings of SIGGRAPH 98, pages 33-42, July 1998. Google ScholarDigital Library
- 13.R. Grzeszczuk, D. Terzopoulos, and G. Hinton. Neuroanimator: Fast neural network emulation and control of physics-based models. P~vceedings of SIG- GRAPH 98, pages 9-20, July 1998. Google ScholarDigital Library
- 14.N.R. Howe, M. E. Leventon, and W. T. Freeman. Bayesian reconstruction of 3d human motion from single-camera video. In S. Solla, T. Leend, and K. Muller, editors, Advances in Neural Information P~vcessing Systems, volume 10. MIT Press, 2000.Google Scholar
- 15.J. Lee and S. Y. Shin. A hierarchical approach to interactive motion editing for human-like figures. P1vceedings of SIGGRAPH 99, pages 39-48, August 1999. Google ScholarDigital Library
- 16.Z. Popovi6 and A. Witkin. Physically based motion transformation. P~vceedings of SIGGRAPH 99, pages 11-20, August 1999. Google ScholarDigital Library
- 17.L.R. Rabiner. A tutorial on hidden Markov models and selected applications in speech recognition. P1vceedings of the IEEE, 77(2):257-286, Feb. 1989.Google Scholar
- 18.C. Rose, M. F. Cohen, and B. Bodenheimer. Verbs and adverbs: Multidimensional motion interpolation. IEEE Computer Graphics & Applications, 18 (5): 32-40, September - October 1998. Google ScholarDigital Library
- 19.J.B. Tenenbaum and W. T. Freeman. Separating style and content. In M. Mozer, M. Jordan, and T. Petsche, editors, Advances in Neural Information P~vcessing Systems, volume 9, pages 662-668. MIT Press, 1997.Google Scholar
- 20.M. Unuma, K. Anjyo, and R. Takeuchi. Fourier principles for emotion-based human figure animation. P~vceedings of SIGGRAPH 95, pages 91-96, August 1995. Google ScholarDigital Library
- 21.A. Wilson and A. Bobick. Parametric hidden markov models for gesture recognition. IEEE Trans. Pattern Analysis and Machine Intelligence, 21(9), 1999. Google ScholarDigital Library
- 22.A. Witkin and Z. Popovi6. Motion warping. Pivceedings of SIGGRAPH 95, pages 105-108, August 1995. Google ScholarDigital Library
- 23.S. C. Zhu, Y. Wu, and D. Mumford. Minimax entropy principle and its applications to texture modeling. Neural Computation, 9(8), 1997. Google ScholarDigital Library
Index Terms
- Style machines
Recommendations
Style components
GI '06: Proceedings of Graphics Interface 2006We propose a novel method for interactive editing of motion data based on motion decomposition. Our method employs Independent Component Analysis (ICA) to separate motion data into visually meaningful components called style components. The user then ...
A style controller for generating virtual human behaviors
AAMAS '11: The 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 3Creating a virtual character that exhibits realistic physical behaviors requires a rich set of animations. To mimic the variety as well as the subtlety of human behavior, we may need to animate not only a wide range of behaviors but also variations of ...
Example-based interpolation of human motion
SIGGRAPH '02: ACM SIGGRAPH 2002 conference abstracts and applicationsGenerating realistic human motions from sparse pose descriptions are important for computer animation and virtual human applications. In this sketch, we propose an example-based motion interpolation technique using independent component analysis (ICA). ...
Comments