mlsanityData to 7 Oct 2026

MetaPose: Fast 3D Pose from Multiple Views without 3D Supervision

arXiv 2108.04869 ↗First posted 10 Aug 2021cs.CV cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

In the era of deep learning, human pose estimation from multiple cameras with unknown calibration has received little attention to date. We show how to train a neural model to perform this task with high precision and minimal latency overhead. The proposed model takes into account joint location uncertainty due to occlusion from multiple views, and requires only 2D keypoint data for training. Our method outperforms both classical bundle adjustment and weakly-supervised monocular 3D baselines on the well-established Human3.6M dataset, as well as the more challenging in-the-wild Ski-Pose PTZ dataset.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 48 of its 76 references that are in the map. First posted on arXiv 10 Aug 2021.

Builds on

48 of 76 references.

References · 48

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  3. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  4. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  5. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  6. 2017End-to-end Recovery of Human Shape and Posecited by 883
  7. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  8. 2016Learning to learn by gradient descent by gradient descentcited by 616
  9. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  10. 2017Self-Normalizing Neural Networkscited by 591
  11. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
  12. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
36 more
  1. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  2. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  3. 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
  4. 2017Learned Primal-dual Reconstructioncited by 251
  5. 2016Panoptic Studio: A Massively Multiview System for Social Interaction Capturecited by 173
  6. 2019Learnable Triangulation of Human Posecited by 160
  7. 2017Solving ill-posed inverse problems using iterative deep neural networkscited by 145
  8. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  9. 2020Epipolar Transformerscited by 117
  10. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 114
  11. 2020Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimationcited by 113
  12. 2019Exploiting temporal context for 3D human pose estimation in the wildcited by 110
  13. 2019Self-Supervised Learning of 3D Human Pose using Multi-view Geometrycited by 98
  14. 2019Unsupervised 3D Pose Estimation with Geometric Self-Supervisioncited by 95
  15. 2020Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flowscited by 94
  16. 2019RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimationcited by 85
  17. 2020Human Body Model Fitting by Learned Gradient Descentcited by 81
  18. 2018Unsupervised Geometry-Aware Representation for 3D Human Pose Estimationcited by 73
  19. 2018Learning Monocular 3D Human Pose Estimation from Multi-view Imagescited by 70
  20. 2020Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wildcited by 66
  21. 2020CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wildcited by 65
  22. 2020MonoClothCap: Towards Temporally Coherent Clothing Capture from Monocular RGB Videocited by 62
  23. 2020Neural Descent for Visual 3D Human Pose and Shapecited by 60
  24. 2018Can 3D Pose be Learned from 2D Projections Alone?cited by 44
  25. 2020Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesiscited by 44
  26. 2020Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPScited by 36
  27. 2020Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimationcited by 36
  28. 2020Motion Capture from Internet Videoscited by 33
  29. 2019Multiview-Consistent Semi-Supervised Learning for 3D Human Pose Estimationcited by 31
  30. 2020Beyond Weak Perspective for Monocular 3D Human Pose Estimationcited by 29
  31. 2018LS-Net: Learning to Solve Nonlinear Least Squares for Monocular Stereocited by 28
  32. 2020SMPLy Benchmarking 3D Human Pose Estimation in the Wildcited by 16
  33. 2018Momen(e)t: Flavor the Moments in Learning to Classify Shapescited by 15
  34. 2021Deep Feedback Inverse Problem Solvercited by 11
  35. 2020MetaFuse: A Pre-trained Fusion Model for Human Pose Estimationcited by 9
  36. 2021Gaussian Mixture Estimation from Weighted Samplescited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 4; 2024: 4; 2025: 1; 2026: 1.

12 papers.

  1. 2023RelPose++: Recovering 6D Poses from Sparse-view Observationscited by 87
  2. 2022SparsePose: Sparse-View Camera Pose Regression and Refinementcited by 53
  3. 2023Markerless human pose estimation for biomedical applications: a surveycited by 13
  4. 2022BKinD-3D: Self-Supervised 3D Keypoint Discovery from Multi-View Videoscited by 10
  5. 2024UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cuescited by 6
  6. 2024Extreme Two-View Geometry From Object Poses with Diffusion Modelscited by 4
  7. 2024EPOCH: Jointly Estimating the 3D Pose of Cameras and Humanscited by 1
  8. 2024Generalizable Single-view Object Pose Estimation by Two-side Generating and Matchingcited by 1
  9. 2026Unconstrained Multi-view Human Pose Estimation with Algebraic Priorscited by 1
  10. 2023Semantic and Articulated Pedestrian Sensing Onboard a Moving Vehiclecited by 0
  11. 2023Two Views Are Better than One: Monocular 3D Pose Estimation with Multiview Consistencycited by 0
  12. 2025Unsupervised Monocular 3D Keypoint Discovery from Multi-View Diffusion Priorscited by 0