Google Open-Sources GNM Head, 3D Parametric Human Head Model

You can import it into Blender using a free add-on.

GNM Head is Google's advanced parametric 3D statistical model of the human head, trained on a "large dataset of 3D scans", not AI-generated. It offers detailed control over facial identity, with 170 head and 80 teeth components, along with 383 expression controls and adjustable head pose.

GNM stands for Generative aNthropomorphic Model and is pronounced "genome," referencing the human genome. It is Google's "ecosystem of parametric human models and perception stacks", which can be integrated into both commercial and open-source software.

"GNM introduces a state-of-the-art family of parametric statistical human models and their associated perception stack. Our roadmap includes releasing a comprehensive suite of statistical models complemented by perception and analysis technology. To facilitate early community research and open development, we are beginning our open-source release with GNM Head, our high-fidelity statistical 3D model of the human head.

The ecosystem is released under a permissive license suitable for both non-commercial and commercial applications."

It also supports multiple frameworks, including NumPy, JAX, PyTorch, and TensorFlow, along with semantic parameter sampling.

There's already a free Blender add-on by Nathan Dickson that imports GNM Head into Blender and lets you adjust sliders for features like ethnicity, gender, and expressions, with live updates on the model:

So far, there's little information available about the data behind the GNM Head model, but more details are expected to be announced soon.

Stay tuned for more details and upcoming GNM releases. Also, subscribe to our Newsletter, join our 80 Level Talent platform, Discord, and follow us on Twitter, LinkedIn, Telegram, and Instagram, where we share breakdowns, the latest news, awesome artworks, and more.

Are you a fan of what we do here at 80 Level? Then make sure to set us as a Preferred Source on Google to see more of our content in your feed.