GNM Head: A Generative aNthropometric Model of the human head

2026-07-26

AI Summary

This work addresses the limitations of existing publicly available head parametric models, which typically capture only external geometry and lack detailed internal anatomical structures such as those inside the mouth and eyes, often due to low-quality input data resulting in insufficient geometric fidelity. To overcome these shortcomings, we propose the first high-fidelity generative model that comprehensively represents full-head anatomy—including eyes, teeth, tongue, and intra-oral and intra-orbital regions—within a unified parametric framework. Our approach integrates large-scale, high-resolution 3D scans with artist-authored, anatomically accurate assets and introduces specialized sub-model architectures to enhance fine-grained detail representation. The method achieves state-of-the-art performance in fitting real-world 3D facial scans and is accompanied by a public release of the complete model framework to support further research and development in the community.

Abstract

Parametric models of the human head are essential tools traditionally used in computer vision and graphics for animation, rendering, and reconstruction. More recently, they serve as crucial conditioning signals within generative large vision models, allowing for tight spatial control of generated imagery. However, existing publicly available models are typically limited in anatomical scope, modeling only outer geometry while ignoring intra-oral and ocular structures, and frequently suffer from reduced geometric quality stemming from low-fidelity input datasets. In this report we introduce a new parametric model dubbed Generative aNthropometric Model (GNM), named as a homophone of the human genome. GNM encompasses the head, face, neck, eyeballs, teeth, and tongue, and it is built on an extensive database of high-resolution 3D scans combined with high-quality anatomy specific artist-made samples. This report details the data provenance, the model architecture including the specialized sub-models for the ocular and intra-oral structures, and shows its SotA performance on fitting target 3D face scans. To foster community innovation, the complete GNM framework is made publicly available.

Problem

• parametric head model
• anatomical completeness
• geometric quality
• intra-oral structures
• ocular structures

Innovation

• parametric head model
• anthropometric modeling
• intra-oral reconstruction
• high-fidelity 3D scanning
• generative vision models