Presentation

<
EVA: Expressive Virtual Avatars from Multi-view Videos
SessionThe Shape of You
DescriptionIn this work, we introduce Expressive Virtual Avatars (EVA), an actor-specific, fully controllable and expressive human avatar framework that achieves high-fidelity, lifelike renderings in real-time, while enabling independent control of facial expressions, body movements, and hand gestures.
Authors
Hendrik Junkawitsch
Max Planck Institute for Informatics
Guoxing Sun
Max Planck Institute for Informatics
Heming Zhu
Max Planck Institute for Informatics
Christian Theobalt
Max Planck Institute for Informatics
Saarbrücken Research Center for Visual Computing, Interaction and Artificial Intelligence
Marc Habermann
Max Planck Institute for Informatics
Saarbrücken Research Center for Visual Computing, Interaction and Artificial Intelligence
Event Type
Technical Paper
TimeThursday, 14 August 20259:50am - 10:00am PDT
LocationWest Building, Rooms 211-214
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 10 August 20256:00pm - 8:45pm PDTWest Building, Ballroom AB
Thursday, 14 August 20259:00am - 10:30am PDTWest Building, Rooms 211-214
Recordings
Livestreamed
Recorded
Next PresentationNext PresentationThe Shape of You - Interactive Discussion
Similar Presentations
Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion
VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control
Controllable Tracking-Based Video Frame Interpolation