Brand, M.E.; Hertzmann, A., “Style Machines”, ACM SIGGRAPH, ISBN: 1-58113-208-5, pps 183-192, July 2000 (Proc ACM Press)
|MERL Report: ||TR2000-14: Matthew Brand, Aaron Hertzmann
|MERL Contact: ||Matthew Brand|
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 style. 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.