mlsanityData to 13 Oct 2026

WorldPose: A World Cup Dataset for Global 3D Human Pose Estimation

arXiv 2501.02771 ↗First posted 6 Jan 2025cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

We present WorldPose, a novel dataset for advancing research in multi-person global pose estimation in the wild, featuring footage from the 2022 FIFA World Cup. While previous datasets have primarily focused on local poses, often limited to a single person or in constrained, indoor settings, the infrastructure deployed for this sporting event allows access to multiple fixed and moving cameras in different stadiums. We exploit the static multi-view setup of HD cameras to recover the 3D player poses and motions with unprecedented accuracy given capture areas of more than 1.75 acres. We then leverage the captured players' motions and field markings to calibrate a moving broadcasting camera. The resulting dataset comprises more than 80 sequences with approx 2.5 million 3D poses and a total traveling distance of over 120 km. Subsequently, we conduct an in-depth analysis of the SOTA methods for global pose estimation. Our experiments demonstrate that WorldPose challenges existing multi-person techniques, supporting the potential for new research in this area and others, such as sports analysis. All pose annotations (in SMPL format), broadcasting camera parameters and footage will be released for academic research purposes.

Key facts. Cited by 13 papers in the map (data through 13 Oct 2026). Builds on 52 of its 81 references that are in the map. First posted on arXiv 6 Jan 2025.

Builds on

52 of 81 references.

References · 52

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  2. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,603
  3. 2017End-to-end Recovery of Human Shape and Posecited by 883
  4. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 816
  5. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  6. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 676
  7. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  8. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 616
  9. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  10. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 452
  11. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 345
  12. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
38 more
  1. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 321
  2. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 304
  3. 2019Resolving 3D Human Pose Ambiguities with 3D Scene Constraintscited by 294
  4. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  5. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 237
  6. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 232
  7. 2020Monocular, One-stage, Regression of Multiple 3D Peoplecited by 216
  8. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  9. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  10. 2022Capturing and Inferring Dense Full-Body Human-Scene Contactcited by 177
  11. 2021GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Camerascited by 152
  12. 2018SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videoscited by 148
  13. 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 141
  14. 2023Decoupling Human and Camera Motion from Videos in the Wildcited by 141
  15. 2021EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devicescited by 136
  16. 2020SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videoscited by 129
  17. 2023EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wildcited by 95
  18. 2023TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environmentscited by 90
  19. 2023Hi4D: 4D Instance Segmentation of Close Human Interactioncited by 87
  20. 2019Fast and Robust Multi-Person 3D Pose Estimation from Multiple Viewscited by 83
  21. 2020Human Body Model Fitting by Learned Gradient Descentcited by 81
  22. 2022Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformerscited by 81
  23. 2021Multi-Person Extreme Motion Predictioncited by 74
  24. 2023EgoHumans: An Egocentric 3D Multi-Human Benchmarkcited by 60
  25. 2022Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Videocited by 59
  26. 20204D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Camerascited by 49
  27. 2023SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environmentscited by 47
  28. 2021VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wildcited by 39
  29. 2022Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projectioncited by 39
  30. 2021KAMA: 3D Keypoint Aware Body Mesh Articulationcited by 27
  31. 2018Sports Camera Calibration via Synthetic Datacited by 26
  32. 2021Shape-aware Multi-Person Pose Estimation from Multi-View Imagescited by 24
  33. 2022BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Trackingcited by 23
  34. 2023TEMPO: Efficient Multi-View Pose Estimation, Tracking, and Forecastingcited by 22
  35. 2018Soccer on Your Tabletopcited by 20
  36. 2023Reconstructing Groups of People with Hypergraph Relational Reasoningcited by 18
  37. 2020Real-Time Camera Pose Estimation for Sports Fieldscited by 17
  38. 2023Crowd3D: Towards Hundreds of People Reconstruction from a Single Imagecited by 12

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 5; 2026: 8.

13 papers.

Sort:

  1. 2025SoccerNet-v3D: Leveraging Sports Broadcast Replays for 3D Scene Understandingcited by 4
  2. 2025PHD: Personalized 3D Human Body Fitting with Point Diffusioncited by 2
  3. 2025Multi-person Physics-based Pose Estimation for Combat Sportscited by 1
  4. 2025HHI-Assist: A Dataset and Benchmark of Human-Human Interaction in Physical Assistance Scenariocited by 1
  5. 2026CalTennis: Large Multi-View Tennis Video Dataset and Benchmark of Monocular-to-3D Pose Estimationcited by 1
  6. 2026SoccerNet 2026 Challenges Resultscited by 1
  7. 2025SoccerTrack v2: A Full-Pitch Panoramic Video Dataset for Game State Reconstruction and Ball Action Spottingcited by 0
  8. 2026SimpliHuMoN: Simplifying Human Motion Predictioncited by 0
  9. 2026Sparkle: A Robust and Versatile Representation for Point Cloud based Human Motion Capturecited by 0
  10. 2026Mesh-Aware Epipolar Matching for Multi-View Multi-Person 3D Pose Estimation in Basketballcited by 0
  11. 2026SMART: SMPLest-X Mesh Adaptation and RAFT Tracking for Soccer Pose Estimationcited by 0
  12. 2026Capturing Uncertainty in Human Motion for Representation Learning in Soccercited by 0
1 more
  1. 2026Field Converter: Geometry-Initialized Temporal Residual Refinement for World-Grounded Player Pose Estimation from Soccer Broadcastscited by 0