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.
Rignerf: Fully controllable neural 3d portraits
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.