mlsanityData to 14 Oct 2026

Exploiting temporal context for 3D human pose estimation in the wild

arXiv 1905.04266 ↗First posted 10 May 2019cs.CVcited by 110

Not on the map. Why?

Abstract (arXiv)

We present a bundle-adjustment-based algorithm for recovering accurate 3D human pose and meshes from monocular videos. Unlike previous algorithms which operate on single frames, we show that reconstructing a person over an entire sequence gives extra constraints that can resolve ambiguities. This is because videos often give multiple views of a person, yet the overall body shape does not change and 3D positions vary slowly. Our method improves not only on standard mocap-based datasets like Human 3.6M -- where we show quantitative improvements -- but also on challenging in-the-wild datasets such as Kinetics. Building upon our algorithm, we present a new dataset of more than 3 million frames of YouTube videos from Kinetics with automatically generated 3D poses and meshes. We show that retraining a single-frame 3D pose estimator on this data improves accuracy on both real-world and mocap data by evaluating on the 3DPW and HumanEVA datasets.

Key facts. Cited by 110 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 43; 2022: 21; 2023: 22; 2024: 14; 2025: 6; 2026: 4.

110 papers.

Sort:

By area:

  1. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 350
  2. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 324
  3. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  4. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 193
  5. 2021Probabilistic Modeling for Human Mesh Recoverycited by 153
  6. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 153
  7. 2021Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphscited by 144
  8. 2023Decoupling Human and Camera Motion from Videos in the Wildcited by 142
  9. 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 135
  10. 2021SimPoE: Simulated Character Control for 3D Human Pose Estimationcited by 114
  11. 2024TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videoscited by 106
  12. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
38 more
  1. 2021Learning Motion Priors for 4D Human Body Capture in 3D Scenescited by 98
  2. 2022TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinementcited by 70
  3. 2021Playing for 3D Human Recoverycited by 64
  4. 2021Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimationcited by 62
  5. 2021DOVE: Learning Deformable 3D Objects by Watching Videoscited by 61
  6. 2021Towards unconstrained joint hand-object reconstruction from RGB videoscited by 58
  7. 2021Estimating Egocentric 3D Human Pose in Global Spacecited by 56
  8. 2022Occluded Human Mesh Recoverycited by 54
  9. 2021THUNDR: Transformer-based 3D HUmaN Reconstruction with Markerscited by 50
  10. 2023HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recoverycited by 49
  11. 2024RoHM: Robust Human Motion Reconstruction via Diffusioncited by 48
  12. 2021Reconstructing 3D Human Pose by Watching Humans in the Mirrorcited by 47
  13. 2023GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Videocited by 47
  14. 2023ReFit: Recurrent Fitting Network for 3D Human Recoverycited by 47
  15. 2021Body Meshes as Pointscited by 45
  16. 20233D Human Mesh Estimation from Virtual Markerscited by 44
  17. 2023Generative Proxemics: A Prior for 3D Social Interaction from Imagescited by 43
  18. 2022D&D: Learning Human Dynamics from Dynamic Cameracited by 41
  19. 2021Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wildcited by 40
  20. 2021Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Drivingcited by 40
  21. 2021Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstructioncited by 39
  22. 2021Adversarial Parametric Pose Priorcited by 38
  23. 2022Learned Vertex Descent: A New Direction for 3D Human Model Fittingcited by 37
  24. 2021Task-Generic Hierarchical Human Motion Prior using VAEscited by 33
  25. 2021AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generationcited by 32
  26. 2021AcinoSet: A 3D Pose Estimation Dataset and Baseline Models for Cheetahs in the Wildcited by 30
  27. 2024PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videoscited by 28
  28. 2021PC-HMR: Pose Calibration for 3D Human Mesh Recovery from 2D Images/Videoscited by 25
  29. 2021Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptationcited by 24
  30. 2022BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Trackingcited by 24
  31. 2024PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarioscited by 24
  32. 2022H3WB: Human3.6M 3D WholeBody Dataset and Benchmarkcited by 23
  33. 2022Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDARcited by 23
  34. 2021Tracking People with 3D Representationscited by 22
  35. 2022HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Drivingcited by 22
  36. 2021Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulationcited by 19
  37. 2021Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networkscited by 16
  38. 2022Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Priorcited by 15

50 most cited of 110 All 110 (JSON)