# From Skin to Skeleton: Towards Biomechanically Accurate 3D Digital Humans

arXiv: https://arxiv.org/abs/2509.06607 · HTML: https://mlsanity.com/paper/2509.06607/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 48 references that are in the map.
- First posted on arXiv 8 Sep 2025.

## Builds on (most cited first, 14 of 14)

- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [VIBE: Video Inference for Human Body Pose and Shape Estimation](https://mlsanity.com/paper/1912.05656/) (2019)
- [BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion](https://mlsanity.com/paper/2306.16940/) (2023)
- [Markerless tracking of user-defined features with deep learning](https://mlsanity.com/paper/1804.03142/) (2018)
- [AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time](https://mlsanity.com/paper/2211.03375/) (2022)
- [STAR: Sparse Trained Articulated Human Body Regressor](https://mlsanity.com/paper/2008.08535/) (2020)
- [3D Human Pose Estimation via Intuitive Physics](https://mlsanity.com/paper/2303.18246/) (2023)
- [Accurate 3D Body Shape Regression using Metric and Semantic Attributes](https://mlsanity.com/paper/2206.07036/) (2022)
- [OSSO: Obtaining Skeletal Shape from Outside](https://mlsanity.com/paper/2204.10129/) (2022)
- [BOSS: Bones, Organs and Skin Shape Model](https://mlsanity.com/paper/2303.04923/) (2023)
- [Towards Single Camera Human 3D-Kinematics](https://mlsanity.com/paper/2301.05435/) (2023)

## Built on by (most cited first, 27 of 27)

- [InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation](https://mlsanity.com/paper/2509.09555/) (2025)
- [MHR: Momentum Human Rig](https://mlsanity.com/paper/2511.15586/) (2025)
- [Non-Rigid 3D Shape Correspondences: From Foundations to Open Challenges and Opportunities](https://mlsanity.com/paper/2604.01274/) (2026)
- [PEAR: Pixel-aligned Expressive humAn mesh Recovery](https://mlsanity.com/paper/2601.22693/) (2026)
- [BFSM: 3D Bidirectional Face-Skull Morphable Model](https://mlsanity.com/paper/2509.24577/) (2025)
- [SKEL-CF: Coarse-to-Fine Biomechanical Skeleton and Surface Mesh Recovery](https://mlsanity.com/paper/2511.20157/) (2025)
- [From 3D Pose to Prose: Biomechanics-Grounded Vision--Language Coaching](https://mlsanity.com/paper/2603.26938/) (2026)
- [What Makes a Good Generated Image? Investigating Human and Multimodal LLM Image Preference Alignment](https://mlsanity.com/paper/2509.12750/) (2025)
- [SAM4Dcap: Training-free Biomechanical Twin System from Monocular Video](https://mlsanity.com/paper/2602.13760/) (2026)
- [BioGait-VLM: A Tri-Modal Vision-Language-Biomechanics Framework for Interpretable Clinical Gait Assessment](https://mlsanity.com/paper/2603.08564/) (2026)
- [Scaling Whole-Body Human Musculoskeletal Behavior Emulation for Specificity and Diversity](https://mlsanity.com/paper/2603.29332/) (2026)
- [PIAvatar: Physically Interactive Avatars via Deformation Gradient Decoupling](https://mlsanity.com/paper/2606.21162/) (2026)
- [Biomechanical 3D Body: Self-Supervised Distillation of Biomechanical Pose from a 3D Body Foundation Model](https://mlsanity.com/paper/2608.29928/) (2026)
- [mmHRI: Towards Privacy-Preserving Human-Robot Interaction with Millimeter-Wave Radar](https://mlsanity.com/paper/2609.34220/) (2026)
- [Learning Neural Parametric 3D Breast Shape Models for Metrical Surface Reconstruction From Monocular RGB Videos](https://mlsanity.com/paper/2510.13540/) (2025)
- [UnrealPose: Leveraging Game Engine Kinematics for Large-Scale Synthetic Human Pose Data](https://mlsanity.com/paper/2601.00991/) (2026)
- [BBoxMaskPose v2: Expanding Mutual Conditioning to 3D](https://mlsanity.com/paper/2601.15200/) (2026)
- [Aligning Fetal Anatomy with Kinematic Tree Log-Euclidean PolyRigid Transforms](https://mlsanity.com/paper/2603.02371/) (2026)
- [Towards Automated Initial Probe Placement in Transthoracic Teleultrasound Using Human Mesh and Skeleton Recovery](https://mlsanity.com/paper/2603.11257/) (2026)
- [ResiHMR: Residual-Limb Aware Single-Image 3D Human Mesh Recovery for Individuals with Limb Loss](https://mlsanity.com/paper/2604.28025/) (2026)
- [BioHuman: Learning Biomechanical Human Representations from Video](https://mlsanity.com/paper/2605.14772/) (2026)
- [Natural Human Motion Recovery by Aligning High-Order Temporal Dynamics from Monocular Videos](https://mlsanity.com/paper/2605.26879/) (2026)
- [SOMA: From Surface Observations to Muscle Anatomy](https://mlsanity.com/paper/2606.09246/) (2026)
- [Pose-to-Biomechanics: Bridging 3D Human Pose Estimation and Biomechanical Attribute Prediction](https://mlsanity.com/paper/2607.08725/) (2026)
- [Revisiting Euler-Angle Regression with Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2607.09650/) (2026)
- [Direct Clinical Joint Angle Extraction from Parametric Body Model Rotation Matrices](https://mlsanity.com/paper/2607.17639/) (2026)
- [PACT: End-to-End Learning of Human Pose, Contacts, and Forces from Video](https://mlsanity.com/paper/2610.00451/) (2026)

## Abstract (arXiv)

Great progress has been made in estimating 3D human pose and shape from images and video by training neural networks to directly regress the parameters of parametric human models like SMPL. However, existing body models have simplified kinematic structures that do not correspond to the true joint locations and articulations in the human skeletal system, limiting their potential use in biomechanics. On the other hand, methods for estimating biomechanically accurate skeletal motion typically rely on complex motion capture systems and expensive optimization methods. What is needed is a parametric 3D human model with a biomechanically accurate skeletal structure that can be easily posed. To that end, we develop SKEL, which re-rigs the SMPL body model with a biomechanics skeleton. To enable this, we need training data of skeletons inside SMPL meshes in diverse poses. We build such a dataset by optimizing biomechanically accurate skeletons inside SMPL meshes from AMASS sequences. We then learn a regressor from SMPL mesh vertices to the optimized joint locations and bone rotations. Finally, we re-parametrize the SMPL mesh with the new kinematic parameters. The resulting SKEL model is animatable like SMPL but with fewer, and biomechanically-realistic, degrees of freedom. We show that SKEL has more biomechanically accurate joint locations than SMPL, and the bones fit inside the body surface better than previous methods. By fitting SKEL to SMPL meshes we are able to "upgrade" existing human pose and shape datasets to include biomechanical parameters. SKEL provides a new tool to enable biomechanics in the wild, while also providing vision and graphics researchers with a better constrained and more realistic model of human articulation. The model, code, and data are available for research at https://skel.is.tue.mpg.de..