mlsanityData to 14 Oct 2026

Hand Keypoint Detection in Single Images using Multiview Bootstrapping

arXiv 1704.07809 ↗First posted 25 Apr 2017cs.CVcited by 231

Not on the map. Why?

Abstract (arXiv)

We present an approach that uses a multi-camera system to train fine-grained detectors for keypoints that are prone to occlusion, such as the joints of a hand. We call this procedure multiview bootstrapping: first, an initial keypoint detector is used to produce noisy labels in multiple views of the hand. The noisy detections are then triangulated in 3D using multiview geometry or marked as outliers. Finally, the reprojected triangulations are used as new labeled training data to improve the detector. We repeat this process, generating more labeled data in each iteration. We derive a result analytically relating the minimum number of views to achieve target true and false positive rates for a given detector. The method is used to train a hand keypoint detector for single images. The resulting keypoint detector runs in realtime on RGB images and has accuracy comparable to methods that use depth sensors. The single view detector, triangulated over multiple views, enables 3D markerless hand motion capture with complex object interactions.

Key facts. Cited by 231 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 62; 2022: 46; 2023: 38; 2024: 34; 2025: 32; 2026: 18.

231 papers.

Sort:

By area:

  1. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 737
  2. 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 490
  3. 2022HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interactioncited by 327
  4. 2021DexYCB: A Benchmark for Capturing Hand Grasping of Objectscited by 325
  5. 2022ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulationcited by 312
  6. 2023Reconstructing Hands in 3D with Transformerscited by 306
  7. 2021H2O: Two Hands Manipulating Objects for First Person Interaction Recognitioncited by 254
  8. 2023InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactionscited by 206
  9. 2021Fake It Till You Make It: Face analysis in the wild using synthetic data alonecited by 200
  10. 2022Embodied Hands: Modeling and Capturing Hands and Bodies Togethercited by 181
  11. 2021FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integrationcited by 169
  12. 2024OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-oncited by 151
38 more
  1. 2021Collaborative Regression of Expressive Bodies using Moderationcited by 137
  2. 2022OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interactioncited by 131
  3. 2024WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wildcited by 124
  4. 2023MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusioncited by 117
  5. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  6. 2023EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wildcited by 97
  7. 2022Interacting Attention Graph for Single Image Two-Hand Reconstructioncited by 87
  8. 2023HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Videocited by 78
  9. 2023Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmarkcited by 75
  10. 2021Neural Monocular 3D Human Motion Capture with Physical Awarenesscited by 71
  11. 2021Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Cameracited by 70
  12. 2023LooseControl: Lifting ControlNet for Generalized Depth Conditioningcited by 68
  13. 2023X-Avatar: Expressive Human Avatarscited by 66
  14. 2023AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimationcited by 64
  15. 2024HumanVid: Demystifying Training Data for Camera-controllable Human Image Animationcited by 64
  16. 2021Towards unconstrained joint hand-object reconstruction from RGB videoscited by 58
  17. 2024ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactionscited by 57
  18. 2022Collaborative Learning for Hand and Object Reconstruction with Attention-guided Graph Convolutioncited by 54
  19. 2021I2UV-HandNet: Image-to-UV Prediction Network for Accurate and High-fidelity 3D Hand Mesh Modelingcited by 52
  20. 2021A Skeleton-Driven Neural Occupancy Representation for Articulated Handscited by 50
  21. 2022UmeTrack: Unified multi-view end-to-end hand tracking for VRcited by 50
  22. 2024Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mambacited by 45
  23. 2022LiDAR-aid Inertial Poser: Large-scale Human Motion Capture by Sparse Inertial and LiDAR Sensorscited by 44
  24. 2023Neural Haircut: Prior-Guided Strand-Based Hair Reconstructioncited by 43
  25. 2021Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentationcited by 40
  26. 2022Pose for Everything: Towards Category-Agnostic Pose Estimationcited by 36
  27. 2024EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wildcited by 36
  28. 2022Reconstructing Hand-Held Objects from Monocular Videocited by 35
  29. 2023A Dataset of Relighted 3D Interacting Handscited by 35
  30. 2024Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objectscited by 35
  31. 2021Contrastive Representation Learning for Hand Shape Estimationcited by 34
  32. 20233D Hand Pose Estimation in Everyday Egocentric Imagescited by 34
  33. 2021Toward Accurate and Realistic Outfits Visualization with Attention to Detailscited by 33
  34. 2021Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Camerascited by 33
  35. 2024GigaHands: A Massive Annotated Dataset of Bimanual Hand Activitiescited by 33
  36. 2021TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimationcited by 32
  37. 2023Human101: Training 100+FPS Human Gaussians in 100s from 1 Viewcited by 32
  38. 2021Hand Image Understanding via Deep Multi-Task Learningcited by 31

50 most cited of 231 All 231 (JSON)