mlsanityData to 7 Oct 2026

AddBiomechanics Dataset: Capturing the Physics of Human Motion at Scale

arXiv 2406.18537 ↗First posted 16 May 2024cs.CV cs.AI cs.GRcited by 11

Not on the map. Why?

Abstract (arXiv)

While reconstructing human poses in 3D from inexpensive sensors has advanced significantly in recent years, quantifying the dynamics of human motion, including the muscle-generated joint torques and external forces, remains a challenge. Prior attempts to estimate physics from reconstructed human poses have been hampered by a lack of datasets with high-quality pose and force data for a variety of movements. We present the AddBiomechanics Dataset 1.0, which includes physically accurate human dynamics of 273 human subjects, over 70 hours of motion and force plate data, totaling more than 24 million frames. To construct this dataset, novel analytical methods were required, which are also reported here. We propose a benchmark for estimating human dynamics from motion using this dataset, and present several baseline results. The AddBiomechanics Dataset is publicly available at https://addbiomechanics.org/download_data.html.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 23 of its 80 references that are in the map. First posted on arXiv 16 May 2024.

Builds on

23 of 80 references.

References · 23

  1. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  2. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  3. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  4. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  5. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 365
  6. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 344
  7. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 319
  8. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  9. 2021Character Controllers Using Motion VAEscited by 182
  10. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  11. 2022Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensorscited by 144
  12. 2021SimPoE: Simulated Character Control for 3D Human Pose Estimationcited by 111
11 more
  1. 2021Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robotscited by 95
  2. 2020Contact and Human Dynamics from Monocular Videocited by 94
  3. 2021Neural Monocular 3D Human Motion Capture with Physical Awarenesscited by 70
  4. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion modelscited by 65
  5. 2020Multi-expert learning of adaptive legged locomotioncited by 62
  6. 2019Estimating 3D Motion and Forces of Person-Object Interactions from Monocular Videocited by 48
  7. 2022Trajectory Optimization for Physics-Based Reconstruction of 3d Human Pose from Monocular Videocited by 37
  8. 2022UnderPressure: Deep Learning for Foot Contact Detection, Ground Reaction Force Estimation and Footskate Cleanupcited by 15
  9. 2023GroundLink: A Dataset Unifying Human Body Movement and Ground Reaction Dynamicscited by 13
  10. 2023DROP: Dynamics Responses from Human Motion Prior and Projective Dynamicscited by 10
  11. 2022Learning to Estimate External Forces of Human Motion in Videocited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 6.

11 papers.

  1. 2024ImDy: Human Inverse Dynamics from Imitated Observationscited by 9
  2. 2024MotionWavelet: Human Motion Prediction via Wavelet Manifold Learningcited by 8
  3. 2026OpenCap Monocular: 3D Human Kinematics and Musculoskeletal Dynamics from a Single Smartphone Videocited by 7
  4. 2024Homogeneous Dynamics Space for Heterogeneous Humanscited by 1
  5. 2025Grounding Intelligence in Movementcited by 1
  6. 2026Towards Real-World Wearable Motion Reconstructioncited by 1
  7. 2025Improving Human Motion Plausibility with Body Momentumcited by 0
  8. 2026BadmintonGRF: A Multimodal Dataset and Benchmark for Markerless Ground Reaction Force Estimation in Badmintoncited by 0
  9. 2026Gravity-guided Contact Dynamics Estimation from 3D Human Motionscited by 0
  10. 2026Pose-to-Biomechanics: Bridging 3D Human Pose Estimation and Biomechanical Attribute Predictioncited by 0
  11. 2026Learning human joint torques from pixelscited by 0