# SOMA: From Surface Observations to Muscle Anatomy

arXiv: https://arxiv.org/abs/2606.09246 · HTML: https://mlsanity.com/paper/2606.09246/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 68 references that are in the map.
- First posted on arXiv 8 Jun 2026.

## Builds on (most cited first, 25 of 25)

- [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)
- [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)
- [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://mlsanity.com/paper/1909.12828/) (2019)
- [VIBE: Video Inference for Human Body Pose and Shape Estimation](https://mlsanity.com/paper/1912.05656/) (2019)
- [NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction](https://mlsanity.com/paper/2212.05231/) (2022)
- [STAR: Sparse Trained Articulated Human Body Regressor](https://mlsanity.com/paper/2008.08535/) (2020)
- [DeepCap: Monocular Human Performance Capture Using Weak Supervision](https://mlsanity.com/paper/2003.08325/) (2020)
- [LiveCap: Real-time Human Performance Capture from Monocular Video](https://mlsanity.com/paper/1810.02648/) (2018)
- [TriHuman : A Real-time and Controllable Tri-plane Representation for Detailed Human Geometry and Appearance Synthesis](https://mlsanity.com/paper/2312.05161/) (2023)
- [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)
- [Viser: Imperative, Web-based 3D Visualization in Python](https://mlsanity.com/paper/2507.22885/) (2025)
- [Reconstructing Humans with a Biomechanically Accurate Skeleton](https://mlsanity.com/paper/2503.21751/) (2025)
- [SoftSMPL: Data-driven Modeling of Nonlinear Soft-tissue Dynamics for Parametric Humans](https://mlsanity.com/paper/2004.00326/) (2020)
- [Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Cameras](https://mlsanity.com/paper/2312.07423/) (2023)
- [VINECS: Video-based Neural Character Skinning](https://mlsanity.com/paper/2307.00842/) (2023)
- [Learning a Generalized Physical Face Model From Data](https://mlsanity.com/paper/2402.19477/) (2024)
- [EMU: Efficient Muscle Simulation In Deformation Space](https://mlsanity.com/paper/2006.08821/) (2020)
- [Capturing Detailed Deformations of Moving Human Bodies](https://mlsanity.com/paper/2102.07343/) (2021)
- [Reconstructing Human Pose from Inertial Measurements: A Generative Model-based Compressive Sensing Approach](https://mlsanity.com/paper/2310.20228/) (2023)
- [Muscles in Time: Learning to Understand Human Motion by Simulating Muscle Activations](https://mlsanity.com/paper/2411.00128/) (2024)
- [Efficient Incremental Potential Contact for Actuated Face Simulation](https://mlsanity.com/paper/2312.02999/) (2023)
- [TailorMe: Self-Supervised Learning of an Anatomically Constrained Volumetric Human Shape Model](https://mlsanity.com/paper/2312.02173/) (2023)

## Abstract (arXiv)

With the growing demand for realistic virtual humans, parametric body models have become a cornerstone of modern medicine, sports, and entertainment applications. However, most of these models are inherently limited: they only capture the 3D surface of the skin, offering no insight into the complex bio-mechanical structures that generate motion. As more applications expand towards biomechanics, the need for virtual human models that go beyond the skin has become increasingly evident. Traditional soft-tissue simulations, such as FEM, are accurate but non-scalable and too computationally expensive for most common applications. Alternatively, existing biomechanical tools can simulate muscular forces and activations, but do not model changes in external shape, restricting how activations correlate with actual observable anatomy. This motivates a novel inverse research problem: recovering muscle deformations directly from visible surface observations - i.e., from the skin, and thus the pose. In this work, we present SOMA (from Surface Observations to Muscle Anatomy), a person-specific model that infers spatio-temporal muscle behavior from surface signals obtained using RGB cameras, and SKIM, a subject-specific soft-tissue deformation dataset. To the best of our knowledge, this is the first method that attempts to recover muscle deformations from multi-view RGB data. We show how our method provides anatomically grounded animations without the complexity of traditional simulations, leading to a scalable and cost-effective solution. Data and code are available.