“Animating the Gesture Style of Particular Individuals”
Michael Neff, UC Davis
Date: Friday, February 12th
Time: 12:00pm
Place: Engineering 2, Room 599
Hosted By: Professor Marilyn Walker, Dept. of Computer Science
This lecture is free and open to the public, but visitors should purchase a parking pass from the visitor kiosk at the main entrance. There they can also provide a map showing the best parking for Engineering 2.
Abstract
In this talk, I will provide an overview of some of the work we have done
towards building gesture animation systems. The motivating goal of this
work is to develop systems that take novel text as input and provide as
output an animated character that says the text while gesticulating
appropriately in the style of a specified target subject. Our process
starts with video or motion capture of a person whose gesturing style we
wish to imitate. An analysis of this data is used to build a statistical
model of the person’s particular gesturing style. Using this model and
input text tagged with theme, rheme and focus, our generation algorithm
creates a gesture script. This script is passed to an animation system,
which enhances the gesture description with additional detail. It then
generates either kinematic or physically simulated motion based on this
description. The system is capable of generating gesture animations for
novel text that are consistent with a given performer’s style, as was
successfully validated in an empirical user study. Time permitting, I
will also discuss recent work on modeling lower body movement and new
tools for analysis-based synthesis.
Michael Neff is an assistant professor in Computer Science and
Technocultural Studies at the University of California, Davis. Before
coming to Davis, he was a post-doctoral fellow at the Max Planck Institute
for Informatics in Saarbruecken, Germany. In 2005, he completed his
Ph.D. in computer science at the University of Toronto. His main research
interests focus on character animation, in particular, the modeling of
expressive movement, physics-based animation, human gesture, animation
tools and the application of performing arts knowledge to computer
animation. At Davis, he is working to bridge the art and technology
communities on campus, collaborating with computer scientists, dancers,
choreographers and geologists. He is the recipient of an NSF CAREER
Award, the Alain Fournier Award for his dissertation (2005) and a best
paper award from Intelligent Virtual Agents (2007).
