mlsanityData to 7 Oct 2026

SVMAC: Unsupervised 3D Human Pose Estimation from a Single Image with Single-view-multi-angle Consistency

arXiv 2106.05616 ↗First posted 10 Jun 2021cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Recovering 3D human pose from 2D joints is still a challenging problem, especially without any 3D annotation, video information, or multi-view information. In this paper, we present an unsupervised GAN-based model consisting of multiple weight-sharing generators to estimate a 3D human pose from a single image without 3D annotations. In our model, we introduce single-view-multi-angle consistency (SVMAC) to significantly improve the estimation performance. With 2D joint locations as input, our model estimates a 3D pose and a camera simultaneously. During training, the estimated 3D pose is rotated by random angles and the estimated camera projects the rotated 3D poses back to 2D. The 2D reprojections will be fed into weight-sharing generators to estimate the corresponding 3D poses and cameras, which are then mixed to impose SVMAC constraints to self-supervise the training process. The experimental results show that our method outperforms the state-of-the-art unsupervised methods on Human 3.6M and MPI-INF-3DHP. Moreover, qualitative results on MPII and LSP show that our method can generalize well to unknown data.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 34 of its 47 references that are in the map. First posted on arXiv 10 Jun 2021.

Builds on

34 of 47 references.

References · 34

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2017Improved Training of Wasserstein GANscited by 2,223
  4. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  5. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  6. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  7. 2017End-to-end Recovery of Human Shape and Posecited by 883
  8. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 515
  9. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  10. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  11. 2016Convolutional Pose Machinescited by 325
  12. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
22 more
  1. 2017Integral Human Pose Regressioncited by 255
  2. 2017VNect: Real-time 3D Human Pose Estimation with a Single RGB Cameracited by 129
  3. 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
  4. 2015DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimationcited by 117
  5. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 114
  6. 20163D Human Pose Estimation = 2D Pose Estimation + Matchingcited by 112
  7. 2019DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Comparecited by 100
  8. 2019Self-Supervised Learning of 3D Human Pose using Multi-view Geometrycited by 98
  9. 2019Unsupervised 3D Pose Estimation with Geometric Self-Supervisioncited by 95
  10. 20183D Human Pose Estimation in the Wild by Adversarial Learningcited by 86
  11. 2019RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimationcited by 85
  12. 2017Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Imagecited by 73
  13. 2018Unsupervised Geometry-Aware Representation for 3D Human Pose Estimationcited by 73
  14. 2020Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wildcited by 66
  15. 2020CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wildcited by 65
  16. 2016Human pose estimation via Convolutional Part Heatmap Regressioncited by 51
  17. 2018Can 3D Pose be Learned from 2D Projections Alone?cited by 44
  18. 2020Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesiscited by 44
  19. 2017Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervisioncited by 27
  20. 2016Single Image 3D Interpreter Networkcited by 19
  21. 2018Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locationscited by 18
  22. 2019Weakly-Supervised 3D Pose Estimation from a Single Image using Multi-View Consistencycited by 8

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1.

3 papers.

  1. 2023MAS: Multi-view Ancestral Sampling for 3D motion generation using 2D diffusioncited by 37
  2. 2023Semantic and Articulated Pedestrian Sensing Onboard a Moving Vehiclecited by 0
  3. 2024Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimescited by 0