Modeling spatial and temporal variation in motion data
- 1 December 2009
- journal article
- conference paper
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 28 (5), 1-10
- https://doi.org/10.1145/1618452.1618517
Abstract
We present a novel method to model and synthesize variation in motion data. Given a few examples of a particular type of motion as input, we learn a generative model that is able to synthesize a family of spatial and temporal variants that are statistically similar to the input examples. The new variants retain the features of the original examples, but are not exact copies of them. We learn a Dynamic Bayesian Network model from the input examples that enables us to capture properties of conditional independence in the data, and model it using a multivariate probability distribution. We present results for a variety of human motion, and 2D handwritten characters. We perform a user study to show that our new variants are less repetitive than typical game and crowd simulation approaches of re-playing a small number of existing motion clips. Our technique can synthesize new variants efficiently and has a small memory requirementKeywords
This publication has 23 references indexed in Scilit:
- Generalizing motion edits with Gaussian processesACM Transactions on Graphics, 2009
- Clone attack! Perception of crowd varietyACM Transactions on Graphics, 2008
- Constraint-based motion optimization using a statistical dynamic modelACM Transactions on Graphics, 2007
- Reconstructing dynamic regulatory mapsMolecular Systems Biology, 2007
- Style translation for human motionACM Transactions on Graphics, 2005
- Motion textureACM Transactions on Graphics, 2002
- Author Index for Volume 10Thyroid®, 2000
- Verbs and adverbs: multidimensional motion interpolationIEEE Computer Graphics and Applications, 1998
- Interpolation synthesis of articulated figure motionIEEE Computer Graphics and Applications, 1997
- Real time responsive animation with personalityIEEE Transactions on Visualization and Computer Graphics, 1995