google/GNM

Health v2 · maintenance only

Flags: no_releases young

Adoption not part of the score

1469 stars · 168 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

GNM is an open ecosystem of parametric statistical human models and perception stacks from Google, starting with GNM Head, a high-fidelity 3D morphable model of the human head with controllable identity, expression, pose, and internal anatomy. It provides multi-framework backends for NumPy, JAX, PyTorch, and TensorFlow under an Apache 2.0 license.

Use cases

• generate 3D human head meshes with controllable identity and expression
• fit a 3D morphable model to face images or scans
• sample statistically plausible head shapes for synthetic data generation
• model eyeballs, teeth, and tongue anatomy in 3D avatars
• build face perception or reconstruction pipelines in PyTorch or JAX
• create digital humans for graphics and generative AI research

When to choose

• you need a state-of-the-art, openly licensed 3DMM of the human head
• you want multi-framework support (NumPy, JAX, PyTorch, TensorFlow)
• you need fine-grained disentangled control over identity, expression, and pose
• you require internal anatomy like eyeballs, teeth, and tongue in head models

When to avoid

• you need full-body parametric human models rather than heads
• you need a ready-made application or GUI rather than a modeling library
• your project depends on models not yet released in the ecosystem roadmap

Facets

library · maturity active

machine-learning computer-vision graphics simulation sdk computer-vision graphics artificial-intelligence machine-learning python cross-platform 3dmm parametric-model digital-human 3d-face human-head-model jax pytorch tensorflow numpy

Member repositories

For agents

markdown · JSON · MCP: product_card(name="google/GNM")