AI RESEARCH

PortraitDirector: A Hierarchical Disentanglement Framework for Controllable and Real-time Facial Reenactment

arXiv CS.CV

ArXi:2604.19129v1 Announce Type: new Existing facial reenactment methods struggle with a trade-off between expressiveness and fine-grained controllability. Holistic facial reenactment models often sacrifice granular control for expressiveness, while methods designed for control may struggle with fidelity and robust disentanglement. Instead of treating facial motion as a monolithic signal, we explore an alternative compositional perspective. In this paper, we