# MonoMSK: Monocular 3D Musculoskeletal Dynamics Estimation

Source: [MonoMSK: Monocular 3D Musculoskeletal Dynamics Estimation](<https://www.sota2.com/research/paper/6925387dd6b0dd334292f8e7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-03T05:00:04.966Z

Authors: Farnoosh Koleini, Hongfei Xue, Ahmed Helmy, Pu Wang

Published: 2025-11-24T17:20:17.000Z

## Abstract

Reconstructing biomechanically realistic 3D human motion - recovering both kinematics (motion) and kinetics (forces) - is a critical challenge. While marker-based systems are lab-bound and slow, popular monocular methods use oversimplified, anatomically inaccurate models (e.g., SMPL) and ignore physics, fundamentally limiting their biomechanical fidelity. In this work, we introduce MonoMSK, a hybrid framework that bridges data-driven learning and physics-based simulation for biomechanically realistic 3D human motion estimation from monocular video. MonoMSK jointly recovers both kinematics (motions) and kinetics (forces and torques) through an anatomically accurate musculoskeletal model. By integrating transformer-based inverse dynamics with differentiable forward kinematics and dynamics layers governed by ODE-based simulation, MonoMSK establishes a physics-regulated inverse-forward loop that enforces biomechanical causality and physical plausibility. A novel forward-inverse consistency loss further aligns motion reconstruction with the underlying kinetic reasoning. Experiments on BML-MoVi, BEDLAM, and OpenCap show that MonoMSK significantly outperforms state-of-the-art methods in kinematic accuracy, while for the first time enabling precise monocular kinetics estimation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [3D Human Motion Estimation on OpenCap](<https://www.sota2.com/research/sota/3d-human-motion-estimation-on-opencap.md>): 3D Human Motion Estimation; OpenCap; MAE (Angle): 2.84.

- [3D human motion estimation on BML-MoVi](<https://www.sota2.com/research/sota/3d-human-motion-estimation-on-bml-movi.md>): 3D Human Motion Estimation; BML-MoVi; MPBLPE: 24.36.

- [3D human motion estimation on BEDLAM](<https://www.sota2.com/research/sota/3d-human-motion-estimation-on-bedlam.md>): 3D Human Motion Estimation; BEDLAM; MPBLPE: 25.62.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2511.19326>)

[PDF](<https://arxiv.org/pdf/2511.19326.pdf>)