mlsanityData to 14 Oct 2026

Self-Supervised 3D Human Pose Estimation with Multiple-View Geometry

arXiv 2108.07777 ↗First posted 17 Aug 2021cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

We present a self-supervised learning algorithm for 3D human pose estimation of a single person based on a multiple-view camera system and 2D body pose estimates for each view. To train our model, represented by a deep neural network, we propose a four-loss function learning algorithm, which does not require any 2D or 3D body pose ground-truth. The proposed loss functions make use of the multiple-view geometry to reconstruct 3D body pose estimates and impose body pose constraints across the camera views. Our approach utilizes all available camera views during training, while the inference is single-view. In our evaluations, we show promising performance on Human3.6M and HumanEva benchmarks, while we also present a generalization study on MPI-INF-3DHP dataset, as well as several ablation results. Overall, we outperform all self-supervised learning methods and reach comparable results to supervised and weakly-supervised learning approaches. Our code and models are publicly available

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 35 of its 51 references that are in the map. First posted on arXiv 17 Aug 2021.

Builds on

35 of 51 references.

References · 35

  1. 2017Mask R-CNNcited by 7,277
  2. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  3. 2017End-to-end Recovery of Human Shape and Posecited by 885
  4. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  5. 2017Wasserstein GANcited by 639
  6. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  7. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  8. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  9. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
  10. 2018PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Modelcited by 133
  11. 2020Epipolar Transformerscited by 117
  12. 20163D Human Pose Estimation = 2D Pose Estimation + Matchingcited by 113
23 more
  1. 2019Self-Supervised Learning of 3D Human Pose using Multi-view Geometrycited by 98
  2. 2019Unsupervised 3D Pose Estimation with Geometric Self-Supervisioncited by 95
  3. 2020Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flowscited by 94
  4. 2017Towards Accurate Markerless Human Shape and Pose Estimation over Timecited by 92
  5. 2019Cross View Fusion for 3D Human Pose Estimationcited by 90
  6. 2019RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimationcited by 85
  7. 20163D Human Pose Estimation from a Single Image via Distance Matrix Regressioncited by 73
  8. 2018Unsupervised Geometry-Aware Representation for 3D Human Pose Estimationcited by 73
  9. 2019C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motioncited by 61
  10. 2015Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Videocited by 54
  11. 2018Can 3D Pose be Learned from 2D Projections Alone?cited by 44
  12. 2020Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesiscited by 44
  13. 2018OriNet: A Fully Convolutional Network for 3D Human Pose Estimationcited by 28
  14. 2017Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervisioncited by 27
  15. 2020Traffic Control Gesture Recognition for Autonomous Vehiclescited by 24
  16. 2014Robust Estimation of 3D Human Poses from a Single Imagecited by 23
  17. 2016Single Image 3D Interpreter Networkcited by 19
  18. 2018Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locationscited by 18
  19. 2015Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approachcited by 16
  20. 2019Forecasting People Trajectories and Head Poses by Jointly Reasoning on Tracklets and Visletscited by 13
  21. 2020Self-Supervised Multi-View Synchronization Learning for 3D Pose Estimationcited by 9
  22. 2020PoseNet3D: Learning Temporally Consistent 3D Human Pose via Knowledge Distillationcited by 8
  23. 2017A Dual-Source Approach for 3D Human Pose Estimation from a Single Imagecited by 7

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 3; 2023: 3; 2024: 1.

10 papers.

  1. 2022MotionMixer: MLP-based 3D Human Body Pose Forecastingcited by 42
  2. 2021Generalizable Human Pose Triangulationcited by 24
  3. 2024Weakly-supervised Camera Localization by Ground-to-satellite Image Registrationcited by 15
  4. 2023Weakly Supervised Multi-Modal 3D Human Body Pose Estimation for Autonomous Drivingcited by 8
  5. 2022A Spatio-Temporal Multilayer Perceptron for Gesture Recognitioncited by 5
  6. 2021Learning Temporal 3D Human Pose Estimation with Pseudo-Labelscited by 4
  7. 2021Self-supervised Secondary Landmark Detection via 3D Representation Learningcited by 3
  8. 2022Multi-person 3D pose estimation from unlabelled datacited by 2
  9. 2023Gesture Recognition with Keypoint and Radar Stream Fusion for Automated Vehiclescited by 1
  10. 2023Efficient, Self-Supervised Human Pose Estimation with Inductive Prior Tuningcited by 1