MMTalker maps speech to 3D face motion via multi-resolution UV sampling and residual-GCN plus dual cross-attention multimodal fusion, reporting better lip and eye sync than prior methods.
Available: https://arxiv.org/abs/2007.08547
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
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
MMTalker: Multiresolution 3D Talking Head Synthesis with Multimodal Feature Fusion
MMTalker maps speech to 3D face motion via multi-resolution UV sampling and residual-GCN plus dual cross-attention multimodal fusion, reporting better lip and eye sync than prior methods.