mlsanityData to 14 Oct 2026

Heuristic Weakly Supervised 3D Human Pose Estimation

arXiv 2105.10996 ↗First posted 23 May 2021cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Monocular 3D human pose estimation from RGB images has attracted significant attention in recent years. However, recent models depend on supervised training with 3D pose ground truth data or known pose priors for their target domains. 3D pose data is typically collected with motion capture devices, severely limiting their applicability. In this paper, we present a heuristic weakly supervised 3D human pose (HW-HuP) solution to estimate 3D poses in when no ground truth 3D pose data is available. HW-HuP learns partial pose priors from 3D human pose datasets and uses easy-to-access observations from the target domain to estimate 3D human pose and shape in an optimization and regression cycle. We employ depth data for weak supervision during training, but not inference. We show that HW-HuP meaningfully improves upon state-of-the-art models in two practical settings where 3D pose data can hardly be obtained: human poses in bed, and infant poses in the wild. Furthermore, we show that HW-HuP retains comparable performance to cutting-edge models on public benchmarks, even when such models train on 3D pose data.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 41 of its 80 references that are in the map. First posted on arXiv 23 May 2021.

Builds on

41 of 80 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  5. 2017End-to-end Recovery of Human Shape and Posecited by 885
  6. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  7. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  8. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  9. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  10. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  11. 2017Neural 3D Mesh Renderercited by 437
  12. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
29 more
  1. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  2. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  3. 2019Resolving 3D Human Pose Ambiguities with 3D Scene Constraintscited by 295
  4. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  5. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  6. 2021Mesh Graphormercited by 265
  7. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  8. 2018Learning to Estimate 3D Human Pose and Shape from a Single Color Imagecited by 226
  9. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
  10. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  11. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  12. 2019Learnable Triangulation of Human Posecited by 161
  13. 2019Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Imagecited by 132
  14. 20163D Human Pose Estimation = 2D Pose Estimation + Matchingcited by 113
  15. 2019Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representationcited by 87
  16. 2020Human Body Model Fitting by Learned Gradient Descentcited by 81
  17. 2018Unsupervised Geometry-Aware Representation for 3D Human Pose Estimationcited by 73
  18. 2019A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Imagecited by 56
  19. 20203D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Trainingcited by 54
  20. 2017MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Priorcited by 36
  21. 2020Bodies at Rest: 3D Human Pose and Shape Estimation from a Pressure Image using Synthetic Datacited by 34
  22. 20183D Human Pose Estimation in RGBD Images for Robotic Task Learningcited by 33
  23. 20163D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Informationcited by 28
  24. 2017Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervisioncited by 27
  25. 2020Invariant Representation Learning for Infant Pose Estimation with Small Datacited by 20
  26. 2018Learning and Tracking the 3D Body Shape of Freely Moving Infants from RGB-D sequencescited by 19
  27. 2019Seeing Under the Cover: A Physics Guided Learning Approach for In-Bed Pose Estimationcited by 17
  28. 2015Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approachcited by 16
  29. 2019Towards Robust RGB-D Human Mesh Recoverycited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 0; 2026: 1.

3 papers.

  1. 2022Computer Vision to the Rescue: Infant Postural Symmetry Estimation from Incongruent Annotationscited by 4
  2. 2023Challenges in Video-Based Infant Action Recognition: A Critical Examination of the State of the Artcited by 0
  3. 2026Natural Human Motion Recovery by Aligning High-Order Temporal Dynamics from Monocular Videoscited by 0