A shared global Gaussian field plus identity embeddings lets a 3D talking head model adapt to new speakers with a few seconds of footage while improving quality over prior per-identity models.
What comprises a good talking-head video generation?
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
-
Few-Shot Identity Adaptation for 3D Talking Heads via Global Gaussian Field
A shared global Gaussian field plus identity embeddings lets a 3D talking head model adapt to new speakers with a few seconds of footage while improving quality over prior per-identity models.