mlsanityData to 7 Oct 2026

VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data

arXiv 2207.09949 ↗First posted 20 Jul 2022cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

While monocular 3D pose estimation seems to have achieved very accurate results on the public datasets, their generalization ability is largely overlooked. In this work, we perform a systematic evaluation of the existing methods and find that they get notably larger errors when tested on different cameras, human poses and appearance. To address the problem, we introduce VirtualPose, a two-stage learning framework to exploit the hidden "free lunch" specific to this task, i.e. generating infinite number of poses and cameras for training models at no cost. To that end, the first stage transforms images to abstract geometry representations (AGR), and then the second maps them to 3D poses. It addresses the generalization issue from two aspects: (1) the first stage can be trained on diverse 2D datasets to reduce the risk of over-fitting to limited appearance; (2) the second stage can be trained on diverse AGR synthesized from a large number of virtual cameras and poses. It outperforms the SOTA methods without using any paired images and 3D poses from the benchmarks, which paves the way for practical applications. Code is available at https://github.com/wkom/VirtualPose.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 37 of its 50 references that are in the map. First posted on arXiv 20 Jul 2022.

Builds on

37 of 50 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2019Objects as Pointscited by 1,172
  5. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  6. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  7. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  8. 2017Integral Human Pose Regressioncited by 255
  9. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 220
  10. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  11. 2020Long-term Human Motion Prediction with Scene Contextcited by 191
  12. 2019Learnable Triangulation of Human Posecited by 160
25 more
  1. 2019Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Imagecited by 131
  2. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 114
  3. 2018LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Imagescited by 88
  4. 20183D Human Pose Estimation in the Wild by Adversarial Learningcited by 86
  5. 2019RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimationcited by 85
  6. 2020Cascaded deep monocular 3D human pose estimation with evolutionary training datacited by 80
  7. 20163D Human Pose Estimation from a Single Image via Distance Matrix Regressioncited by 73
  8. 2020SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimationcited by 52
  9. 2020HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimationcited by 44
  10. 2020AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wildcited by 40
  11. 2021VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wildcited by 39
  12. 2021Context Modeling in 3D Human Pose Estimation: A Unified Perspectivecited by 37
  13. 2020Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimationcited by 36
  14. 2020MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimationcited by 35
  15. 2020Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric Approachcited by 27
  16. 2020Reconstructing NBA Playerscited by 24
  17. 2014Robust Estimation of 3D Human Poses from a Single Imagecited by 23
  18. 2017Deep Multitask Architecture for Integrated 2D and 3D Human Sensingcited by 21
  19. 2020HDNet: Human Depth Estimation for Multi-Person Camera-Space Localizationcited by 20
  20. 2019Multi-Person 3D Human Pose Estimation from Monocular Imagescited by 19
  21. 2022Dual networks based 3D Multi-Person Pose Estimation from Monocular Videocited by 13
  22. 2019PoseLifter: Absolute 3D human pose lifting network from a single noisy 2D human posecited by 10
  23. 2019Absolute Human Pose Estimation with Depth Prediction Networkcited by 9
  24. 20183D Interpreter Networks for Viewer-Centered Wireframe Modelingcited by 5
  25. 2020Multi-Person Absolute 3D Human Pose Estimation with Weak Depth Supervisioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 3; 2024: 3; 2025: 1; 2026: 1.

10 papers.

  1. 20233D Human Mesh Estimation from Virtual Markerscited by 44
  2. 2022PLIKS: A Pseudo-Linear Inverse Kinematic Solver for 3D Human Body Estimationcited by 18
  3. 2023Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wildcited by 11
  4. 2022Progressive Multi-view Human Mesh Recovery with Self-Supervisioncited by 9
  5. 2023ProxyCap: Real-time Monocular Full-body Capture in World Space via Human-Centric Proxy-to-Motion Learningcited by 9
  6. 2024Reconstructing Close Human Interactions from Multiple Viewscited by 7
  7. 2024Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recoverycited by 4
  8. 2024Exploring the Impact of Synthetic Data for Aerial-view Human Detectioncited by 3
  9. 2026MuPPet: Multi-person 2D-to-3D Pose Liftingcited by 2
  10. 2025Systematic Comparison of Projection Methods for Monocular 3D Human Pose Estimation on Fisheye Imagescited by 1