A self-supervised domain adaptation technique enables high-fidelity face models to be driven from monocular commodity camera footage without target domain labels by leveraging consecutive frame texture consistency.
Estimating 3D shape and texture using pixel intensity, edges, specular highlights, texture constraints and a prior
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Self-Supervised Adaptation of High-Fidelity Face Models for Monocular Performance Tracking
A self-supervised domain adaptation technique enables high-fidelity face models to be driven from monocular commodity camera footage without target domain labels by leveraging consecutive frame texture consistency.