Style machines

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,et al.  An inequality and associated maximization technique in statistical estimation of probabilistic functions of a Markov process , 1972 .

[2]  Lawrence R. Rabiner,et al.  A tutorial on Hidden Markov Models , 1986 .

[3]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[4]  Zoran Popovic,et al.  Motion warping , 1995, SIGGRAPH.

[5]  Ken-ichi Anjyo,et al.  Fourier principles for emotion-based human figure animation , 1995, SIGGRAPH.

[6]  Lance Williams,et al.  Motion signal processing , 1995, SIGGRAPH.

[7]  Gaston H. Gonnet,et al.  On the LambertW function , 1996, Adv. Comput. Math..

[8]  Joshua B. Tenenbaum,et al.  Separating Style and Content , 1996, NIPS.

[9]  Joshua B. Tenenbaum,et al.  Learning bilinear models for two-factor problems in vision , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  Michael Gleicher,et al.  Motion editing with spacetime constraints , 1997, SI3D.

[11]  Christoph Bregler,et al.  Learning and recognizing human dynamics in video sequences , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Song-Chun Zhu,et al.  Minimax Entropy Principle and Its Application to Texture Modeling , 1997, Neural Computation.

[13]  Joachim M. Buhmann,et al.  Empirical Risk Approximation: An Induction Principle for Unsupervised Learning , 1998 .

[14]  Michael Gleicher,et al.  Retargetting motion to new characters , 1998, SIGGRAPH.

[15]  Geoffrey E. Hinton,et al.  NeuroAnimator: fast neural network emulation and control of physics-based models , 1998, SIGGRAPH.

[16]  Michael F. Cohen,et al.  Verbs and Adverbs: Multidimensional Motion Interpolation , 1998, IEEE Computer Graphics and Applications.

[17]  Zoran Popovic,et al.  Physically based motion transformation , 1999, SIGGRAPH.

[18]  Matthew Brand,et al.  Shadow puppetry , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[19]  JeheeLee SungYongShin.  A Hierarchical Approach to Interactive Motion Editing for Human-like Figures , 1999 .

[20]  Matthew Brand,et al.  Voice puppetry , 1999, SIGGRAPH.

[21]  Aaron F. Bobick,et al.  Parametric Hidden Markov Models for Gesture Recognition , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  William T. Freeman,et al.  Bayesian Reconstruction of 3D Human Motion from Single-Camera Video , 1999, NIPS.

[23]  Matthew Brand,et al.  Pattern discovery via entropy minimization , 1999, AISTATS.

[24]  Sung Yong Shin,et al.  A hierarchical approach to interactive motion editing for human-like figures , 1999, SIGGRAPH.

[25]  Matthew Brand,et al.  Finding Variational Structure in Data by Cross-Entropy Optimization , 2000, ICML.