AI RESEARCH

LPM 1.0: Video-based Character Performance Model

arXiv CS.CV

ArXi:2604.07823v1 Announce Type: new Performance, the externalization of intent, emotion, and personality through visual, vocal, and temporal behavior, is what makes a character alive. Learning such performance from video is a promising alternative to traditional 3D pipelines. However, existing video models struggle to jointly achieve high expressiveness, real-time inference, and long-horizon identity stability, a tension we call the performance trilemma.