Component-based locomotion composition

  • Authors:
  • Yejin Kim;Michael Neff

  • Affiliations:
  • Department of Computer Science and Program for Cinema and Technocultural Studies, University of California, Davis;Department of Computer Science and Program for Cinema and Technocultural Studies, University of California, Davis

  • Venue:
  • EUROSCA'12 Proceedings of the 11th ACM SIGGRAPH / Eurographics conference on Computer Animation
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

When generating locomotion, it is particularly challenging to adjust the motion's style. This paper introduces a component-based system for human locomotion composition that drives off a set of example locomotion clips. The distinctive style of each example is analyzed in the form of sub-motion components decomposed from separate body parts via independent component analysis (ICA). During the synthesis process, we use these components as combinatorial ingredients to generate new locomotion sequences that are stylistically different from the example set. Our system is designed for novice users who do not have much knowledge of important locomotion properties, such as the correlations throughout the body. Thus, the proposed system analyzes the examples in a unsupervised manner and synthesizes an output locomotion from a small number of control parameters. Our experimental results show that the system can generate physically plausible locomotion in a desired style at interactive speed.