SDTalk proposes a generalizable one-shot 3DGS talking head method that uses structured facial priors for complete reconstruction and dual-branch motion fields for dynamics, outperforming prior identity-specific approaches.
Flow-guided one-shot talk- ing face generation with a high-resolution audio-visual dataset
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SDTalk: Structured Facial Priors and Dual-Branch Motion Fields for Generalizable Gaussian Talking Head Synthesis
SDTalk proposes a generalizable one-shot 3DGS talking head method that uses structured facial priors for complete reconstruction and dual-branch motion fields for dynamics, outperforming prior identity-specific approaches.