mlsanityData to 14 Oct 2026

CoMotion: Concurrent Multi-person 3D Motion

arXiv 2504.12186 ↗First posted 16 Apr 2025cs.CV cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

We introduce an approach for detecting and tracking detailed 3D poses of multiple people from a single monocular camera stream. Our system maintains temporally coherent predictions in crowded scenes filled with difficult poses and occlusions. Our model performs both strong per-frame detection and a learned pose update to track people from frame to frame. Rather than match detections across time, poses are updated directly from a new input image, which enables online tracking through occlusion. We train on numerous image and video datasets leveraging pseudo-labeled annotations to produce a model that matches state-of-the-art systems in 3D pose estimation accuracy while being faster and more accurate in tracking multiple people through time. Code and weights are provided at https://github.com/apple/ml-comotion

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 49 of its 57 references that are in the map. First posted on arXiv 16 Apr 2025.

Builds on

49 of 57 references.

References · 49

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  3. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  4. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  5. 2017End-to-end Recovery of Human Shape and Posecited by 885
  6. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 712
  7. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  8. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  9. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 518
  10. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  11. 2020FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Trackingcited by 490
  12. 2019Tracking without bells and whistlescited by 382
37 more
  1. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 381
  2. 2020TransTrack: Multiple Object Tracking with Transformercited by 371
  3. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 350
  4. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  5. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 337
  6. 2018Learning 3D Human Dynamics from Videocited by 316
  7. 2019Towards Real-Time Multi-Object Trackingcited by 311
  8. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 272
  9. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  10. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 238
  11. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 236
  12. 2024Sapiens: Foundation for Human Vision Modelscited by 229
  13. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  14. 2021DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motioncited by 217
  15. 2023WHAM: Reconstructing World-grounded Humans with Accurate 3D Motioncited by 206
  16. 2017PoseTrack: A Benchmark for Human Pose Estimation and Trackingcited by 173
  17. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 159
  18. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 153
  19. 2017Towards Accurate Multi-person Pose Estimation in the Wildcited by 131
  20. 2024TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videoscited by 106
  21. 2024Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shotcited by 101
  22. 2023PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimationcited by 92
  23. 2023TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environmentscited by 91
  24. 2023MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Trackingcited by 88
  25. 2023EgoHumans: An Egocentric 3D Multi-Human Benchmarkcited by 60
  26. 2024Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimationcited by 59
  27. 2017Detect-and-Track: Efficient Pose Estimation in Videoscited by 51
  28. 2024RoHM: Robust Human Motion Reconstruction via Diffusioncited by 48
  29. 2023ReFit: Recurrent Fitting Network for 3D Human Recoverycited by 47
  30. 2023PACE: Human and Camera Motion Estimation from in-the-wild Videoscited by 34
  31. 2024WHAC: World-grounded Humans and Camerascited by 30
  32. 20233D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimationcited by 28
  33. 2016ArtTrack: Articulated Multi-person Tracking in the Wildcited by 27
  34. 2023Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimationcited by 26
  35. 2023Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Videocited by 25
  36. 2021Tracking People by Predicting 3D Appearance, Location & Posecited by 15
  37. 2023IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiationcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 11.

13 papers.

Sort:

By area:

  1. 2026RAM: Recover Any 3D Human Motion in-the-Wildcited by 12
  2. 2026MotionWeaver: Holistic 4D-Anchored Framework for Multi-Humanoid Image Animationcited by 3
  3. 2026U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generationcited by 2
  4. 2026Multi-HMR 2: Multi-Person Camera-Centric Human Detection, Mesh Recovery and Trackingcited by 2
  5. 2026LAMP: Localization Aware Multi-camera People Tracking in Metric 3D Worldcited by 1
  6. 2026DETRAM: End-to-end DEtection, Tracking and Recovery of HumAn Meshescited by 1
  7. 2025ShowMak3r: Compositional TV Show Reconstructioncited by 0
  8. 2025Grounding Foundational Vision Models with 3D Human Poses for Robust Action Recognitioncited by 0
  9. 2026Patient4D: Temporally Consistent Patient Body Mesh Recovery from Monocular Operating Room Videocited by 0
  10. 2026Learning Quantised Structure-Preserving Motion Representations for Dance Fingerprintingcited by 0
  11. 2026SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidancecited by 0
  12. 20264D Human-Scene Reconstruction from Low-Overlap Capturescited by 0
1 more
  1. 2026Everybody Tracking Every Bodycited by 0