Drivable Volumetric Avatars Using Texel-aligned Features
Event Type
Technical Paper
Interest Areas
Research & Education
Presentation Types
Registration Categories
Full Conference Supporter
Full Conference
Virtual Conference Supporter
Virtual Conference
Exhibitor Additional Full Conference
Exhibitor Full Conference
DescriptionWe propose a framework for modeling and driving full-body avatars of real people. We introduce a novel volumetric representation that supports driving of clothed avatars through texel-aligned features — a localized representation that leverages both the structural prior of a skeleton-based parametric model and observed sparse image signals at the same time.