Welcome to the GNM Ecosystem repository. GNM - pronounced as genome (/ˈdʒiː.noʊm/) in reference to the human genome - strives to be the most accurate and complete 3D parametric human model.
3D Morphable Models (3DMMs) are widely used across computer vision, computer graphics, and generative AI for representing human geometry and appearance. GNM introduces a state-of-the-art family of parametric statistical human models and its 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.
Here we list all the available GNM packages:
| Name | Description | Chips | Teaser |
|---|---|---|---|
| Parametric 3D statistical human head and face geometry model providing fine-grained, disentangled control over identity, expressions, and head pose. The model contains controllable internal anatomy including eyeballs, teeth and tongue. Includes multi-framework backend support for NumPy, JAX, PyTorch, and TensorFlow, along with semantic parameter sampling. | |||
If you use any part of the GNM Ecosystem in your work, please consider citing the corresponding package. Relevant bibtex entries can be found in the individual packages. We'd love to accept your patches and contributions to this project! See CONTRIBUTING.md for more information on how to get started and how we handle external contributions.
This project is licensed under the Apache License, Version 2.0. See the LICENSE file for details.