OT-Talk trains a HuBERT-transformer-ChebNet model with a sliced Wasserstein distance loss on mesh-as-probability-measure representations and reports the best lip and face errors on VOCASET and Multiface.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
OT-Talk: Animating 3D Talking Head with Optimal Transportation
OT-Talk trains a HuBERT-transformer-ChebNet model with a sliced Wasserstein distance loss on mesh-as-probability-measure representations and reports the best lip and face errors on VOCASET and Multiface.