AI RESEARCH
ISExplore:Informative Segment Selection for Efficient Personalized 3D Talking Face Generation
arXiv CS.CV
•
ArXi:2511.07940v2 Announce Type: replace Talking Face Generation (TFG) methods based on Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have recently achieved impressive progress in personalized talking head synthesis. However, existing methods typically require several minutes of reference video for meticulous preprocessing and fitting, resulting in hours of preparation time and limiting their practical applicability.