# Biomechanical 3D Body: Self-Supervised Distillation of Biomechanical Pose from a 3D Body Foundation Model

arXiv: https://arxiv.org/abs/2608.29928 · HTML: https://mlsanity.com/paper/2608.29928/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 43 references that are in the map.
- First posted on arXiv 30 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016)
- [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://mlsanity.com/paper/1909.12828/) (2019)
- [Sapiens: Foundation for Human Vision Models](https://mlsanity.com/paper/2408.12569/) (2024)
- [WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion](https://mlsanity.com/paper/2312.07531/) (2023)
- [Equinox: neural networks in JAX via callable PyTrees and filtered transformations](https://mlsanity.com/paper/2111.00254/) (2021)
- [SAM 3D Body: Robust Full-Body Human Mesh Recovery](https://mlsanity.com/paper/2602.15989/) (2026)
- [MoVi: A Large Multipurpose Motion and Video Dataset](https://mlsanity.com/paper/2003.01888/) (2020)
- [Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats](https://mlsanity.com/paper/2212.14474/) (2022)
- [From Skin to Skeleton: Towards Biomechanically Accurate 3D Digital Humans](https://mlsanity.com/paper/2509.06607/) (2025)
- [OSSO: Obtaining Skeletal Shape from Outside](https://mlsanity.com/paper/2204.10129/) (2022)
- [Reconstructing Humans with a Biomechanically Accurate Skeleton](https://mlsanity.com/paper/2503.21751/) (2025)
- [Differentiable Biomechanics Unlocks Opportunities for Markerless Motion Capture](https://mlsanity.com/paper/2402.17192/) (2024)
- [BioPose: Biomechanically-accurate 3D Pose Estimation from Monocular Videos](https://mlsanity.com/paper/2501.07800/) (2025)
- [ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling](https://mlsanity.com/paper/2508.15767/) (2025)
- [Differentiable Biomechanics for Markerless Motion Capture in Upper Limb Stroke Rehabilitation: A Comparison with Optical Motion Capture](https://mlsanity.com/paper/2411.14992/) (2024)
- [OpenCap Monocular: 3D Human Kinematics and Musculoskeletal Dynamics from a Single Smartphone Video](https://mlsanity.com/paper/2603.24733/) (2026)
- [Monocular Biomechanical Tracking of Fingers with Inverse Kinematics to Foundation Models](https://mlsanity.com/paper/2605.09258/) (2026)
- [Calibrated Uncertainty for Trustworthy Clinical Gait Analysis Using Probabilistic Multiview Markerless Motion Capture](https://mlsanity.com/paper/2601.22412/) (2026)
- [Sapiens2](https://mlsanity.com/paper/2604.21681/) (2026)

## Built on by (most cited first, 1 of 1)

- [Cross-Model Distillation of a Human-Pose Foundation Model from Unannotated Infant Video for Markerless 3D Pose Estimation](https://mlsanity.com/paper/2609.01840/) (2026)

## Abstract (arXiv)

State-of-the-art monocular body recovery methods predict mesh vertices and angles on the corresponding kinematic tree, but their outputs lack biomechanically defined joint angles that downstream applications like clinical and biomechanical analyses require. We extend an existing foundation model, SAM-3D-Body, with an additional biomechanical prediction head that, from a single RGB image, regresses the joint angles and scales of a biomechanical model. Training this model presents a challenge, as there are limited datasets of paired images and biomechanical fits. To overcome this, we supervise biomechanical outputs with in-loop optimized targets from a Levenberg-Marquardt solver performing inverse kinematics fits against markers from the mesh predictions. This allows distilling the biomechanical head from the mesh head, even from unlabeled images. To make this work with GPU-optimized biomechanical models in MuJoCo, the entire model was implemented in JAX using Equinox. We trained this distilled output head on the publicly released SAM-3D-Body dataset. We then validated this model on biomechanical fits to two publicly available marker-based datasets, MoVi and BioCV, as well as movements from a clinical cohort captured with multiview markerless motion capture. The resulting model outperforms existing models for direct regression of biomechanics from images while only slightly underperforming the state-of-the-art monocular biomechanics method that performs more costly inference-time optimization of entire trajectories.