Monocular and Generalizable Gaussian Talking Head Animation

Real-Time Inference on Unseen Identities (>40FPS) Driving Video Single Reference Monucular Training Monucular Dataset "two hundred thousand" Figure 1. MGGTalk is trained using only monocular datasets and enable generalizing to unseen identities without personalized re-training. Additionally, it supports real-time generation of talking heads in diverse poses and novel viewpoints.