GASP trains a Gaussian-avatar prior on synthetic humans, then fits and fine-tunes it to a single photo or monocular video to obtain real-time animatable 360-degree avatars.
Dynamic neural radiance fields for monocular 4d facial avatar reconstruction
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
GASP: Gaussian Avatars with Synthetic Priors
GASP trains a Gaussian-avatar prior on synthetic humans, then fits and fine-tunes it to a single photo or monocular video to obtain real-time animatable 360-degree avatars.