Presentation / Installation
PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modeling
DescriptionWe present a new pose encoding method, PoseVocab, for human avatar modeling. Previous methods usually directly map driving poses to dynamic human appearances through a NeRF MLP, yielding blurry avatars. In contrast, PoseVocab constructs pairs of key poses and learnable pose embeddings to encode high-fidelity human appearances under various poses.
Event Type
Technical Paper
TimeMonday, 7 August 202311:27am - 11:37am PDT
LocationRoom 502 AB
ACM Digital Library
Technical Paper PDF
Session Time & Location
Research & Education
Livestreamed
Recorded
Animation/Simulation
Modeling
FC
FCS
V
VS
EFC