Selecting a short informative reference segment using audio diversity, lip amplitude, and viewpoint criteria achieves comparable personalized 3D talking face quality while reducing processing and training time by over 5x.
Talking face generation by adversarially disentangled audio-visual representation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ISExplore:Informative Segment Selection for Efficient Personalized 3D Talking Face Generation
Selecting a short informative reference segment using audio diversity, lip amplitude, and viewpoint criteria achieves comparable personalized 3D talking face quality while reducing processing and training time by over 5x.