SOMA: From Surface Observations to Muscle Anatomy

• URL: http://arxiv.org/abs/2606.09246v1
• Date: Mon, 08 Jun 2026 09:20:46 GMT
• Title: SOMA: From Surface Observations to Muscle Anatomy
• Abstract summary: We present SOMA, a person-specific model that infers bio-temporal muscle behavior from surface signals obtained using RGB cameras.<n>We show how our method provides anatomically grounded animations without the complexity of traditional simulations.
• Score: 55.23576061150391
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Towards Embodied AI with MuscleMimic: Unlocking full-body musculoskeletal motor learning at scale [38.15316304510102]
  MuscleMimic is an open-source framework for motion imitation learning with physiologically realistic, muscle-driven models.<n>By lowering the computational and data barriers to musculoskeletal simulation, MuscleMimic enables systematic model validation across diverse dynamic movements.
  arXiv  Detail & Related papers  (2026-03-26T15:18:37Z)
• Musculoskeletal simulation of limb movement biomechanics in Drosophila melanogaster [32.89880065783502]
  We introduce the first 3D, data-driven musculoskeletal model of Drosophila legs.<n>Our model incorporates a Hill-type muscle representation based on high-resolution X-ray scans from multiple fixed specimens.<n>Our model enables the investigation of motor control in an experimentally tractable model organism.
  arXiv  Detail & Related papers  (2025-09-08T08:21:14Z)
• Diff-MSM: Differentiable MusculoSkeletal Model for Simultaneous Identification of Human Muscle and Bone Parameters [5.071602765737453]
  We propose using Differentiable MusculoSkeletal Model (Diff-MSM) to simultaneously identify its muscle and bone parameters.<n>The new parameter identification technique with the Diff-MSM has great potential to enable new applications in muscle health monitoring, rehabilitation, and sports science.
  arXiv  Detail & Related papers  (2025-08-18T18:43:43Z)
• Muscles in Time: Learning to Understand Human Motion by Simulating Muscle Activations [64.98299559470503]
  Muscles in Time (MinT) is a large-scale synthetic muscle activation dataset. It contains over nine hours of simulation data covering 227 subjects and 402 simulated muscle strands. We show results on neural network-based muscle activation estimation from human pose sequences.
  arXiv  Detail & Related papers  (2024-10-31T18:28:53Z)
• HUMOS: Human Motion Model Conditioned on Body Shape [54.20419874234214]
  We introduce a new approach to develop a generative motion model based on body shape.<n>We show that it's possible to train this model using unpaired data.<n>The resulting model generates diverse, physically plausible, and dynamically stable human motions.
  arXiv  Detail & Related papers  (2024-09-05T23:50:57Z)
• MS-MANO: Enabling Hand Pose Tracking with Biomechanical Constraints [50.61346764110482]
  We integrate a musculoskeletal system with a learnable parametric hand model, MANO, to create MS-MANO. This model emulates the dynamics of muscles and tendons to drive the skeletal system, imposing physiologically realistic constraints on the resulting torque trajectories. We also propose a simulation-in-the-loop pose refinement framework, BioPR, that refines the initial estimated pose through a multi-layer perceptron network.
  arXiv  Detail & Related papers  (2024-04-16T02:18:18Z)
• Learning a Generalized Physical Face Model From Data [19.58920251013244]
  Physically-based simulation is a powerful approach for 3D facial animation. We propose a generalized physical face model that we learn from a large 3D face dataset. Our model can be quickly fit to any unseen identity and produce a ready-to-animate physical face model automatically.
  arXiv  Detail & Related papers  (2024-02-29T18:59:31Z)
• OstrichRL: A Musculoskeletal Ostrich Simulation to Study Bio-mechanical Locomotion [8.849771760994273]
  We release a 3D musculoskeletal simulation of an ostrich based on the MuJoCo simulator. The model is based on CT scans and dissections used to gather actual muscle data. We also provide a set of reinforcement learning tasks, including reference motion tracking and a reaching task with the neck.
  arXiv  Detail & Related papers  (2021-12-11T19:58:11Z)
• LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies [78.17425779503047]
  We propose a novel neural implicit representation for the human body. It is fully differentiable and optimizable with disentangled shape and pose latent spaces. Our model can be trained and fine-tuned directly on non-watertight raw data with well-designed losses.
  arXiv  Detail & Related papers  (2021-11-30T04:10:57Z)
• Learning Local Recurrent Models for Human Mesh Recovery [50.85467243778406]
  We present a new method for video mesh recovery that divides the human mesh into several local parts following the standard skeletal model. We then model the dynamics of each local part with separate recurrent models, with each model conditioned appropriately based on the known kinematic structure of the human body. This results in a structure-informed local recurrent learning architecture that can be trained in an end-to-end fashion with available annotations.
  arXiv  Detail & Related papers  (2021-07-27T14:30:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.