mlsanityData to 7 Oct 2026

Learning Temporal 3D Human Pose Estimation with Pseudo-Labels

arXiv 2110.07578 ↗First posted 14 Oct 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

We present a simple, yet effective, approach for self-supervised 3D human pose estimation. Unlike the prior work, we explore the temporal information next to the multi-view self-supervision. During training, we rely on triangulating 2D body pose estimates of a multiple-view camera system. A temporal convolutional neural network is trained with the generated 3D ground-truth and the geometric multi-view consistency loss, imposing geometrical constraints on the predicted 3D body skeleton. During inference, our model receives a sequence of 2D body pose estimates from a single-view to predict the 3D body pose for each of them. An extensive evaluation shows that our method achieves state-of-the-art performance in the Human3.6M and MPI-INF-3DHP benchmarks. Our code and models are publicly available at urlhttps://github.com/vru2020/TMHPE/.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 28 of its 35 references that are in the map. First posted on arXiv 14 Oct 2021.

Builds on

28 of 35 references.

References · 28

  1. 2017End-to-end Recovery of Human Shape and Posecited by 883
  2. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  3. 2017Wasserstein GANcited by 635
  4. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  5. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  6. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  7. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  8. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 220
  9. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 114
  10. 2019Self-Supervised Learning of 3D Human Pose using Multi-view Geometrycited by 98
  11. 2019Unsupervised 3D Pose Estimation with Geometric Self-Supervisioncited by 95
  12. 2019RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimationcited by 85
16 more
  1. 2018Learning Monocular 3D Human Pose Estimation from Multi-view Imagescited by 70
  2. 2020Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wildcited by 66
  3. 2020CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wildcited by 65
  4. 2019In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representationscited by 48
  5. 2018Can 3D Pose be Learned from 2D Projections Alone?cited by 44
  6. 2020Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesiscited by 44
  7. 2016Deep Kinematic Pose Regressioncited by 40
  8. 2018OriNet: A Fully Convolutional Network for 3D Human Pose Estimationcited by 28
  9. 2017Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervisioncited by 27
  10. 2020Weakly Supervised Generative Network for Multiple 3D Human Pose Hypothesescited by 25
  11. 2020Traffic Control Gesture Recognition for Autonomous Vehiclescited by 24
  12. 2016Single Image 3D Interpreter Networkcited by 19
  13. 2015Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approachcited by 16
  14. 2019Forecasting People Trajectories and Head Poses by Jointly Reasoning on Tracklets and Visletscited by 13
  15. 2021Self-Supervised 3D Human Pose Estimation with Multiple-View Geometrycited by 10
  16. 2020PoseNet3D: Learning Temporally Consistent 3D Human Pose via Knowledge Distillationcited by 8

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 0; 2025: 1.

4 papers.

  1. 2023Weakly Supervised Multi-Modal 3D Human Body Pose Estimation for Autonomous Drivingcited by 8
  2. 2022A Spatio-Temporal Multilayer Perceptron for Gesture Recognitioncited by 5
  3. 2023A Large-Scale 3D Face Mesh Video Dataset via Neural Re-parameterized Optimizationcited by 5
  4. 2025PRGCN: A Graph Memory Network for Cross-Sequence Pattern Reuse in 3D Human Pose Estimationcited by 0