Presentation

<
Universal Facial Encoding of Codec Avatars From VR Headsets
Session3D Head Avatars From Data
DescriptionWe present a self-supervised and robust encoding algorithm for achieving high-fidelity real-time 3D facial animation, via head-mounted cameras on a consumer VR headset. Our model generalizes to unseen users and variability in illuminations, under incomplete views of the face, enabling accessible authentic avatar-mediated telepresence in VR.
Authors
Shaojie Bai
Facebook Reality Labs
Te-Li Wang
Facebook Reality Labs
Chenghui Li
Facebook Reality Labs
Akshay Venkatesh
Facebook Reality Labs
Tomas Simon
Facebook Reality Labs
Chen Cao
Facebook Reality Labs
Gabriel Schwartz
Facebook Reality Labs
Jason Saragih
Facebook Reality Labs
Yaser Sheikh
Facebook Reality Labs
Shih-En Wei
Facebook Reality Labs
Event Type
Technical Paper
TimeWednesday, 31 July 20249:40am - 9:50am MDT
LocationMile High 1
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 28 July 20246:00pm - 8:45pm MDTBluebird Ballroom
Wednesday, 31 July 20249:00am - 10:30am MDTMile High 1
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Animation
Geometry
Modeling
Rendering
Registration Categories
Full Conference
Full Conference Supporter
Virtual Access
Exhibitor Full Conference
Wednesday
Next PresentationNext PresentationLearning a Generalized Physical Face Model From Data