Google releases GNM, a parametric 3D head model with identity and expression control

rsasaki0109 · x · 2026-07-29

Google’s GNM is a state-of-the-art parametric 3D statistical model of the human head trained on a large set of 3D scans.

It offers fine-grained control over identity, expression, and head pose, and the released package includes NumPy, JAX, PyTorch, and TensorFlow implementations plus visualization and semantic parameter sampling tools. The README also highlights dense face geometry covering skin, eyes, teeth, and tongue.

Related event: Google Open-Sources GNM 3D Head Model(2 posts)→

Original post →

More from Multimodal

Multimodal channel →