“Real-Time Individualized Virtual Humans” by Magnenat-Thalmann and Thalmann
Conference:
Type(s):
Title:
- Real-Time Individualized Virtual Humans
Presenter(s)/Author(s):
Abstract:
The latest techniques for modeling fast, individualized, animatable virtual humans for real-time applications. Because a human is composed of a head and a body, this course analyses how these two parts can be modeled and globally animated. More precisely, it shows how individualized real-time bodies can be automatically generated from scanned data or from interactive measurements and how an automatic skeleton can be created for any body size, animated automatically, controlled in real time, and retargeted according to a motion-sequences database. Other topics include: facial animation from facial motion capture and simulation of interactive, realistic talking virtual humans, including personality models and complete body gestures.
The course also shows how crowds are modeled in real time using dynamic meshes, static meshes, and impostors, and explains techniques for adding variety to crowds, including individual animation, individualized path-planning, and accessories.
Several case studies in cultural heritage, emergency situations, and fasion modeling are presented to illustrate interaction with virtual humans. And the course concludes with a summary of open research topics in the virtual-human field.
Additional Information:
Prerequisites
Familiarity with the fundamentals of computer graphics and computer animation, geometrical methods, collision detection and response, and real-time techniques is highly recommended but not mandatory.
Intended Audience
Developers of real-time virtual worlds, technical directors, researchers, and game developers who are looking for innovation as well as proven methodologies in simulating real-time virtual humans.
