AI RESEARCH
FreeTalk: Emotional Topology-Free 3D Talking Heads
arXiv CS.CV
•
ArXi:2603.15512v1 Announce Type: new Speech-driven 3D facial animation has advanced rapidly, yet most approaches remain tied to registered template meshes, preventing effective deployment on raw 3D scans with arbitrary topology. At the same time, modeling controllable emotional dynamics beyond lip articulation remains challenging, and is often tied to template-based parameterizations.