Open access
2026
Stable and High-Fidelity Photo-Realistic Talking Face Generation Using a Three-Stage Model With Extended Landmarks and Post-Refinement
Experimental results show that the complete landmark representation provides the best overall image-generation performance among the evaluated configurations, while Post-Refinement consistently improves frame-level visual quality.
Zi-Kai Shu, Takashi Nose, A. Ito
· IEEE Access · 0 citations