Human Mesh Modeling for Anny Body

2025-11-05

AI Summary

Existing parametric human models rely on costly 3D scanning and proprietary shape spaces, resulting in narrow demographic coverage and poor openness. This paper introduces Anny: the first differentiable parametric human model built exclusively on WHO demographic statistics and anthropometric priors, enabling semantic-controllable modeling across the full lifespan—from infancy to old age—and accommodating diverse body types and proportions. Its core innovation is an open, continuous, and interpretable cross-age human shape space, decoupled from scan data. Anny employs differentiable rendering and blendshape-based deformation for millimeter-accurate scan fitting and mesh reconstruction. Experiments show that Anny-driven reconstruction achieves performance on par with scan-based baselines while offering superior demographic representativeness and interpretability. The model, source code, and synthetic dataset Anny-One are released under the Apache 2.0 license.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Humans and AI: AI for Accessibility
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Parametric body models are central to many human-centric tasks, yet existing models often rely on costly 3D scans and learned shape spaces that are proprietary and demographically narrow. We introduce Anny, a simple, fully differentiable, and scan-free human body model grounded in anthropometric knowledge from the MakeHuman community. Anny defines a continuous, interpretable shape space, where phenotype parameters (e.g. gender, age, height, weight) control blendshapes spanning a wide range of human forms -- across ages (from infants to elders), body types, and proportions. Calibrated using WHO population statistics, it provides realistic and demographically grounded human shape variation within a single unified model. Thanks to its openness and semantic control, Anny serves as a versatile foundation for 3D human modeling -- supporting millimeter-accurate scan fitting, controlled synthetic data generation, and Human Mesh Recovery (HMR). We further introduce Anny-One, a collection of 800k photorealistic humans generated with Anny, showing that despite its simplicity, HMR models trained with Anny can match the performance of those trained with scan-based body models, while remaining interpretable and broadly representative. The Anny body model and its code are released under the Apache 2.0 license, making Anny an accessible foundation for human-centric 3D modeling.

Problem

• Creating open parametric body models without 3D scans
• Developing demographically inclusive human shape representation
• Enabling interpretable phenotype-controlled human mesh modeling

Innovation

• Differentiable scan-free model using anthropometric knowledge
• Continuous shape space controlled by phenotype parameters
• Calibrated with WHO statistics for demographic realism