Neural Animation Layering for Synthesizing Martial Arts Movements
Event Type
Technical Paper
Interest Areas
Research & Education
Registration Levels
Ultimate Supporter
Ultimate Attendee
Exhibitor Ultimate
DescriptionWe present a modular deep learning framework for animation layering to interactively synthesize novel combinations and variations from different motion skills, demonstrated on martial arts movements. Our system can be used for offline and online motion generation alike, provides an intuitive interface to integrate with animator workflows, and is relevant for real-time applications such as computer games.