Learning Motion Style Synthesis from Perceptual Observations
Abstract
This paper presents an algorithm for synthesis of human motion in specified styles. We use a theory of movement observation (Laban Movement Analysis) to describe movement styles as points in a multi-dimensional perceptual space. We cast the task of learning to synthesize desired movement styles as a regression problem: sequences generated via space-time interpolation of motion capture data are used to learn a nonlinear mapping between animation parameters and movement styles in perceptual space. We demonstrate that the learned model can apply a variety of motion styles to pre-recorded motion sequences and it can extrapolate styles not originally included in the training data.
Cite
Text
Torresani et al. "Learning Motion Style Synthesis from Perceptual Observations." Neural Information Processing Systems, 2006.Markdown
[Torresani et al. "Learning Motion Style Synthesis from Perceptual Observations." Neural Information Processing Systems, 2006.](https://mlanthology.org/neurips/2006/torresani2006neurips-learning/)BibTeX
@inproceedings{torresani2006neurips-learning,
title = {{Learning Motion Style Synthesis from Perceptual Observations}},
author = {Torresani, Lorenzo and Hackney, Peggy and Bregler, Christoph},
booktitle = {Neural Information Processing Systems},
year = {2006},
pages = {1393-1400},
url = {https://mlanthology.org/neurips/2006/torresani2006neurips-learning/}
}