Presentation / Installation


AvatarMAV: Fast 3D Head Avatar Reconstruction Using Motion-aware Neural Voxels
DescriptionWe propose AvatarMAV, which models both the canonical appearance and the decoupled expression motion by time-efficient neural voxels for head avatar. Thus, AvatarMAV can recover photorealistic head avatars in just five minutes (implemented with pure PyTorch), which is significantly faster than the state-of-the-art facial reenactment methods.
Event Type
Technical Paper
TimeWednesday, 9 August 20234:17pm - 4:27pm PDT
ACM Digital Library Technical Paper PDF
Session Time & Location
Sunday, 6 August 20236pm - 8:30pm PDTWest Hall B
Wednesday, 9 August 20233:45pm - 5:15pm PDTPetree Hall C
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Rendering
Video
Registration Categories
FC
FCS
V
VS
EFC