mlsanityData to 7 Oct 2026

Mo2Cap2: Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera

arXiv 1803.05959 ↗First posted 15 Mar 2018cs.CVcited by 67

Not on the map. Why?

Abstract (arXiv)

We propose the first real-time approach for the egocentric estimation of 3D human body pose in a wide range of unconstrained everyday activities. This setting has a unique set of challenges, such as mobility of the hardware setup, and robustness to long capture sessions with fast recovery from tracking failures. We tackle these challenges based on a novel lightweight setup that converts a standard baseball cap to a device for high-quality pose estimation based on a single cap-mounted fisheye camera. From the captured egocentric live stream, our CNN based 3D pose estimation approach runs at 60Hz on a consumer-level GPU. In addition to the novel hardware setup, our other main contributions are: 1) a large ground truth training corpus of top-down fisheye images and 2) a novel disentangled 3D pose estimation approach that takes the unique properties of the egocentric viewpoint into account. As shown by our evaluation, we achieve lower 3D joint error as well as better 2D overlay than the existing baselines.

Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 10; 2023: 11; 2024: 17; 2025: 13; 2026: 7.

67 papers.

Sort:

By area:

  1. 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 477
  2. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 229
  3. 2023Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perceptioncited by 166
  4. 2021Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensorscited by 137
  5. 2021EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devicescited by 136
  6. 2021Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimationcited by 101
  7. 2023EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wildcited by 95
  8. 2022Ego-Body Pose Estimation via Ego-Head Pose Estimationcited by 93
  9. 2022GIMO: Gaze-Informed Human Motion Prediction in Contextcited by 81
  10. 2023EgoHumans: An Egocentric 3D Multi-Human Benchmarkcited by 58
  11. 2021Estimating Egocentric 3D Human Pose in Global Spacecited by 56
  12. 2022UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capturecited by 56
38 more
  1. 2024Estimating Body and Hand Motion in an Ego-sensed Worldcited by 56
  2. 2023EgoLocate: Real-time Motion Capture, Localization, and Mapping with Sparse Body-mounted Sensorscited by 48
  3. 2024EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understandingcited by 35
  4. 2022Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervisioncited by 33
  5. 2022Surround-view Fisheye Camera Perception for Automated Driving: Overview, Survey and Challengescited by 33
  6. 2023Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinementcited by 31
  7. 2022Scene-aware Egocentric 3D Human Pose Estimationcited by 30
  8. 2024Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Cameracited by 30
  9. 2024EventEgo3D: 3D Human Motion Capture from Egocentric Event Streamscited by 29
  10. 2021Egocentric Pose Estimation from Human Vision Spancited by 27
  11. 2022Interaction Replica: Tracking Human-Object Interaction and Scene Changes From Human Motioncited by 27
  12. 2024HMD^2: Environment-aware Motion Generation from Single Egocentric Head-Mounted Devicecited by 26
  13. 2022EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queriescited by 25
  14. 20233D Human Pose Perception from Egocentric Stereo Videoscited by 23
  15. 2023Ego3DPose: Capturing 3D Cues from Binocular Egocentric Viewscited by 22
  16. 2025Challenges and Trends in Egocentric Vision: A Surveycited by 20
  17. 2024Real-Time Simulated Avatar from Head-Mounted Sensorscited by 17
  18. 2025Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Inputcited by 17
  19. 2025EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activitycited by 15
  20. 2021EgoRenderer: Rendering Human Avatars from Egocentric Camera Imagescited by 13
  21. 2024Attention-Propagation Network for Egocentric Heatmap to 3D Pose Liftingcited by 13
  22. 2024SimpleEgo: Predicting Probabilistic Body Pose from Egocentric Camerascited by 12
  23. 2024EMHI: A Multimodal Egocentric Human Motion Dataset with HMD and Body-Worn IMUscited by 12
  24. 2025egoPPG: Heart Rate Estimation from Eye-Tracking Cameras in Egocentric Systems to Benefit Downstream Vision Taskscited by 11
  25. 2024EgoHDM: An Online Egocentric-Inertial Human Motion Capture, Localization, and Dense Mapping Systemcited by 9
  26. 2024A Survey on 3D Egocentric Human Pose Estimationcited by 8
  27. 2024EgoAvatar: Egocentric View-Driven and Photorealistic Full-body Avatarscited by 7
  28. 2025Bring Your Rear Cameras for Egocentric 3D Human Pose Estimationcited by 7
  29. 2024Unsupervised 3D Point Cloud Completion via Multi-view Adversarial Learningcited by 6
  30. 2022Enhancing Egocentric 3D Pose Estimation with Third Person Viewscited by 5
  31. 2024HiSC4D: Human-centered interaction and 4D Scene Capture in Large-scale Space Using Wearable IMUs and LiDARcited by 5
  32. 2025FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Videocited by 5
  33. 2024EgoPoseFormer: A Simple Baseline for Stereo Egocentric 3D Human Pose Estimationcited by 4
  34. 2025ECHO: Ego-Centric modeling of Human-Object interactionscited by 4
  35. 2023Human Pose Estimation in Monocular Omnidirectional Top-View Imagescited by 3
  36. 2023Applications of Deep Learning for Top-View Omnidirectional Imaging: A Surveycited by 3
  37. 2024DragPoser: Motion Reconstruction from Variable Sparse Tracking Signals via Latent Space Optimizationcited by 3
  38. 2025Fish2Mesh Transformer: 3D Human Mesh Recovery from Egocentric Visioncited by 3

50 most cited of 67 All 67 (JSON)