Expressive body animation pipeline for virtual agent

  • Authors:
  • Jing Huang;Catherine Pelachaud

  • Affiliations:
  • Telecom ParisTech - CNRS, Paris, France;Telecom ParisTech - CNRS, Paris, France

  • Venue:
  • IVA'12 Proceedings of the 12th international conference on Intelligent Virtual Agents
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we present our expressive body-gestures animation synthesis model for our Embodied Conversational Agent(ECA) technology. Our implementation builds upon a full body reach model using a hybrid kinematics solution. We describe the full pipeline of our model that starts from a symbolic description of behaviors, to the construction of a set of keyframes till the generation of the whole animation enhanced with expressive qualities. Our approach offers convincing visual quality results obtained with high real-time performance.