AI RESEARCH
VGGT-HPE: Reframing Head Pose Estimation as Relative Pose Prediction
arXiv CS.CV
•
ArXi:2604.10106v1 Announce Type: new Monocular head pose estimation is traditionally formulated as direct regression from a single image to an absolute pose. This paradigm forces the network to implicitly internalize a dataset-specific canonical reference frame. In this work, we argue that predicting the relative rigid transformation between two observed head configurations is a fundamentally easier and robust formulation. We