Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MHR: Momentum Human Rig

Aaron Ferguson, Ahmed A. A. Osman, Berta Bescos, Carsten Stoll, Chris Twigg, Christoph Lassner, David Otte, Eric Vignola, Fabian Prada, Federica Bogo, Igor Santesteban, Javier Romero, Jenna Zarate, Jeongseok Lee, Jinhyung Park, Jinlong Yang, John Doublestein, Kishore Venkateshan, Kris Kitani, Ladislav Kavan, Marco Dal Farra, Matthew Hu, Matthew Cioffi, Michael Fabris, Michael Ranieri, Mohammad Modarres, Petr Kadlecek, Rawal Khirodkar, Rinat Abdrashitov, Romain Prévost, Roman Rajbhandari, Ronald Mallet, Russell Pearsall, Sandy Kao, Sanjeev Kumar, Scott Parrish, Shoou-I Yu, Shunsuke Saito, Takaaki Shiratori, Te-Li Wang, Tony Tung, Yichen Xu, Yuan Dong, Yuhua Chen, Yuanlu Xu, Yuting Ye, Zhongshi Jiang

TL;DR

MHR addresses the need for an expressive, industry-friendly parametric human model with decoupled skeleton and surface control. It extends ATLAS by integrating semantic facial expressions, a partitioned identity space, and a pose-corrective rig that uses local non-linear edits with sparse activations. The model supports 127 joints and 204 pose parameters across multi-resolution levels of detail, enabling robust animation in AR/VR pipelines and beyond. Evaluation on 3DBodyTex demonstrates improved fitting with fewer components and better articulation, while maintaining compatibility with common asset formats. The framework offers practical impact through an open, license-friendly rig for expressive digital humans.

Abstract

We present MHR, a parametric human body model that combines the decoupled skeleton/shape paradigm of ATLAS with a flexible, modern rig and pose corrective system inspired by the Momentum library. Our model enables expressive, anatomically plausible human animation, supporting non-linear pose correctives, and is designed for robust integration in AR/VR and graphics pipelines.

MHR: Momentum Human Rig

TL;DR

MHR addresses the need for an expressive, industry-friendly parametric human model with decoupled skeleton and surface control. It extends ATLAS by integrating semantic facial expressions, a partitioned identity space, and a pose-corrective rig that uses local non-linear edits with sparse activations. The model supports 127 joints and 204 pose parameters across multi-resolution levels of detail, enabling robust animation in AR/VR pipelines and beyond. Evaluation on 3DBodyTex demonstrates improved fitting with fewer components and better articulation, while maintaining compatibility with common asset formats. The framework offers practical impact through an open, license-friendly rig for expressive digital humans.

Abstract

We present MHR, a parametric human body model that combines the decoupled skeleton/shape paradigm of ATLAS with a flexible, modern rig and pose corrective system inspired by the Momentum library. Our model enables expressive, anatomically plausible human animation, supporting non-linear pose correctives, and is designed for robust integration in AR/VR and graphics pipelines.

Paper Structure

This paper contains 12 sections, 5 equations, 9 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. Model
  4. Pose Parametrization
  5. Facial Expressions
  6. Identity Space
  7. Pose Correctives
  8. Implementation Details
  9. Evaluation
  10. Discussion and Future Work
  11. Conclusions
  12. Author Contributions

Figures (9)

  • Figure 1: MHR provides precise, decoupled control of skeletal and surface attributes at different LODs.
  • Figure 2: MHR Skeleton.
  • Figure 3: MHR Skeleton Transformations. Each cell shows the effect of changing one bone (or set of bones) length. Middle body is neutral, left (right) one shows bone length increase in red (blue).
  • Figure 4: MHR Expression Example of four MHR expressions fully activated.
  • Figure 5: Body, head and hand masks for partitioned identity shape space
  • ...and 4 more figures