Research map / 3D vision / Human pose estimation
3D Human Pose Estimation with Muscles
Kevin Zhu, AliAsghar MohammadiNasrabadi, Alexander Wong, John McPhee
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Introduces MusclePose, an end-to-end learnable physics-infused 3D human pose estimator that adds muscle-dynamics modeling to infer human dynamics from monocular video.
Problem
Physics-based 3D human pose estimators try to produce physically plausible poses by enforcing dynamics equations, but this is underconstrained without force-annotated data, so existing methods often estimate kinematics only.
Approach
Integrates muscle-dynamics modeling into an end-to-end learnable physics-infused pose estimator so that muscle forces, rather than only kinematics, are inferred from monocular video.
Closest papers by meaning
- AddBiomechanics Dataset: Capturing the Physics of Human Motion at Scale (ECCV 2024 · similarity 0.91)
- Trajectory Optimization for Physics-Based Reconstruction of 3D Human Pose From Monocular Video (CVPR 2022 · similarity 0.90)
- Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videos (NeurIPS 2024 · similarity 0.89)
- HiPoser: 3D Human Pose Estimation with Hierarchical Shared Learning at Parts-Level Using Inertial Measurement Units (AAAI 2025 · similarity 0.88)
- PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos (CVPR 2024 · similarity 0.88)
- Muscles in Time: Learning to Understand Human Motion In-Depth by Simulating Muscle Activations (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
