Skip to content

← ArchivePaper2025

Human Mesh Modeling for Anny Body

Romain Brégier, Guénolé Fiche, Laura Bravo-Sánchez, Thomas Lucas, Matthieu Armando, Philippe Weinzaepfel, Grégory Rogez, Fabien Baradel

arXivIndustrial10 cites1 descendantRiggingSkinningRetargeting

Anny is a scan-free open-source parametric body model using anthropometric phenotype parameters: gender, age, height, weight, calibrated from WHO population statistics.

Abstract

Parametric body models provide the structural basis for 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 images 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. 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.

How to read this

Category
Method / open resource: a parametric human body model
Contributions
  • Anny, a fully differentiable, scan-free parametric body model grounded in MakeHuman anthropometric knowledge with a continuous, interpretable shape space.
  • Phenotype parameters (gender, age, height, weight) controlling blendshapes across ages and body types, calibrated using WHO population statistics.
  • Anny-One, a collection of 800k photorealistic images, used to show HMR models trained on Anny can match scan-based body models.
Context
Positions itself against scan-based, proprietary, demographically narrow parametric models (the SMPL lineage), substituting anthropometric/MakeHuman priors for learned scan shape spaces.
Correctness
Validated on scan fitting, synthetic data generation and Human Mesh Recovery, with the headline claim that it matches scan-based models on HMR; readers should note the shape space is anthropometrically parameterized rather than learned from scans, so its realism is bounded by the WHO/MakeHuman priors.
Clarity
Accessible framing with interpretable parameters; a first pass conveys the model, do a second pass for the blendshape construction and calibration details.
How to read it
Read the abstract and shape-space definition first; second pass the calibration and the Anny-One HMR comparison if you plan to use it for training data or fitting.

Builds on

Nothing in the archive, this is a starting point.

Built upon by

This page summarises the entry and links to its original source. The archive never hosts or redistributes the publication itself.Show it in the full archive list →