mlsanityData to 14 Oct 2026

Multi-person Physics-based Pose Estimation for Combat Sports

arXiv 2504.08175 ↗First posted 11 Apr 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

We propose a novel framework for accurate 3D human pose estimation in combat sports using sparse multi-camera setups. Our method integrates robust multi-view 2D pose tracking via a transformer-based top-down approach, employing epipolar geometry constraints and long-term video object segmentation for consistent identity tracking across views. Initial 3D poses are obtained through weighted triangulation and spline smoothing, followed by kinematic optimization to refine pose accuracy. We further enhance pose realism and robustness by introducing a multi-person physics-based trajectory optimization step, effectively addressing challenges such as rapid motions, occlusions, and close interactions. Experimental results on diverse datasets, including a new benchmark of elite boxing footage, demonstrate state-of-the-art performance. Additionally, we release comprehensive annotated video datasets to advance future research in multi-person pose estimation for combat sports.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 39 of its 72 references that are in the map. First posted on arXiv 11 Apr 2025.

Builds on

39 of 72 references.

References · 39

  1. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  2. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  3. 2022XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Modelcited by 439
  4. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 272
  5. 2020Monocular, One-stage, Regression of Multiple 3D Peoplecited by 218
  6. 2022Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensorscited by 146
  7. 2023Decoupling Human and Camera Motion from Videos in the Wildcited by 142
  8. 2021SimPoE: Simulated Character Control for 3D Human Pose Estimationcited by 114
  9. 20233D Human Pose Estimation via Intuitive Physicscited by 103
  10. 2022DiffPose: Toward More Reliable 3D Pose Estimationcited by 100
  11. 2019Self-Supervised Learning of 3D Human Pose using Multi-view Geometrycited by 98
  12. 2020Contact and Human Dynamics from Monocular Videocited by 95
27 more
  1. 2023Hi4D: 4D Instance Segmentation of Close Human Interactioncited by 87
  2. 2021MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actionscited by 84
  3. 2019Fast and Robust Multi-Person 3D Pose Estimation from Multiple Viewscited by 83
  4. 2022ViTPose++: Vision Transformer for Generic Body Pose Estimationcited by 65
  5. 2021Direct Multi-view Multi-person 3D Pose Estimationcited by 64
  6. 2022Predictive Sampling: Real-time Behaviour Synthesis with MuJoCocited by 47
  7. 2022D&D: Learning Human Dynamics from Dynamic Cameracited by 41
  8. 2022Differentiable Dynamics for Articulated 3d Human Motion Reconstructioncited by 39
  9. 2021Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereocited by 38
  10. 2022Trajectory Optimization for Physics-Based Reconstruction of 3d Human Pose from Monocular Videocited by 37
  11. 2020Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPScited by 36
  12. 2020Optical Non-Line-of-Sight Physics-based 3D Human Pose Estimationcited by 34
  13. 2022Neural MoCon: Neural Motion Control for Physically Plausible Human Motion Capturecited by 31
  14. 2022Embodied Scene-aware Human Pose Estimationcited by 28
  15. 2023SportsPose -- A Dynamic 3D sports pose datasetcited by 26
  16. 2020Reconstructing NBA Playerscited by 24
  17. 2023Multiple View Geometry Transformers for 3D Human Pose Estimationcited by 19
  18. 2020Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometrycited by 18
  19. 2024MultiPhys: Multi-Person Physics-aware 3D Motion Estimationcited by 18
  20. 2021Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networkscited by 16
  21. 2025BioPose: Biomechanically-accurate 3D Pose Estimation from Monocular Videoscited by 16
  22. 2025WorldPose: A World Cup Dataset for Global 3D Human Pose Estimationcited by 14
  23. 2025AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movementscited by 14
  24. 2023Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wildcited by 11
  25. 2024TeamTrack: A Dataset for Multi-Sport Multi-Object Tracking in Full-pitch Videoscited by 11
  26. 2023A Unified Multi-view Multi-person Tracking Frameworkcited by 5
  27. 2024Pose2Trajectory: Using Transformers on Body Pose to Predict Tennis Player's Trajectorycited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026RAM: Recover Any 3D Human Motion in-the-Wildcited by 12