EVA reconstructs an actor-specific avatar from multi-view video that renders in real time and allows independent control of body motion, hand gestures, and facial expressions through a disentangled two-layer Gaussian representation.
Computer Vision and Pattern Recognition (CVPR) (2019), 10101–10111
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
EVA: Expressive Virtual Avatars from Multi-view Videos
EVA reconstructs an actor-specific avatar from multi-view video that renders in real time and allows independent control of body motion, hand gestures, and facial expressions through a disentangled two-layer Gaussian representation.