mlsanityData to 14 Oct 2026

Unsupervised 3D Keypoint Discovery with Multi-View Geometry

arXiv 2211.12829 ↗First posted 23 Nov 2022cs.CV cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Analyzing and training 3D body posture models depend heavily on the availability of joint labels that are commonly acquired through laborious manual annotation of body joints or via marker-based joint localization using carefully curated markers and capturing systems. However, such annotations are not always available, especially for people performing unusual activities. In this paper, we propose an algorithm that learns to discover 3D keypoints on human bodies from multiple-view images without any supervision or labels other than the constraints multiple-view geometry provides. To ensure that the discovered 3D keypoints are meaningful, they are re-projected to each view to estimate the person's mask that the model itself has initially estimated without supervision. Our approach discovers more interpretable and accurate 3D keypoints compared to other state-of-the-art unsupervised approaches on Human3.6M and MPI-INF-3DHP benchmark datasets.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 37 of its 48 references that are in the map. First posted on arXiv 23 Nov 2022.

Builds on

37 of 48 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  6. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  7. 2015Spatial Transformer Networkscited by 1,429
  8. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  9. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  10. 2017Unsupervised Learning of Disentangled Representations from Videocited by 139
  11. 2018Unsupervised Learning of Object Landmarks through Conditional Image Generationcited by 114
  12. 2019Self-Supervised Learning of 3D Human Pose using Multi-view Geometrycited by 98
25 more
  1. 2019Unsupervised 3D Pose Estimation with Geometric Self-Supervisioncited by 95
  2. 2018Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoningcited by 79
  3. 2018Unsupervised Geometry-Aware Representation for 3D Human Pose Estimationcited by 73
  4. 2018Unsupervised Discovery of Object Landmarks as Structural Representationscited by 73
  5. 2018Learning Monocular 3D Human Pose Estimation from Multi-view Imagescited by 70
  6. 2019Unsupervised Part-Based Disentangling of Object Shape and Appearancecited by 67
  7. 2020Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wildcited by 66
  8. 2020CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wildcited by 65
  9. 2017Unsupervised learning of object landmarks by factorized spatial embeddingscited by 64
  10. 2021KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Controlcited by 51
  11. 2021Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objectscited by 50
  12. 2018Self-supervised learning of a facial attribute embedding from videocited by 45
  13. 2020Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesiscited by 44
  14. 2017Improving Landmark Localization with Semi-Supervised Learningcited by 39
  15. 2019Unsupervised Learning of Landmarks by Descriptor Vector Exchangecited by 39
  16. 2020Unsupervised Learning of Intrinsic Structural Representation Pointscited by 39
  17. 2021ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Posescited by 35
  18. 2021Unsupervised Learning of Visual 3D Keypoints for Controlcited by 30
  19. 2020Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimationcited by 26
  20. 2021Unsupervised Human Pose Estimation through Transforming Shape Templatescited by 26
  21. 2019Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimationcited by 23
  22. 2020Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Setscited by 23
  23. 2019Neural Scene Decomposition for Multi-Person Motion Capturecited by 21
  24. 2021Unsupervised 3D Pose Estimation for Hierarchical Dance Video Recognitioncited by 9
  25. 2020Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimationcited by 7

Built on by

Cited by year

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

2 papers.

  1. 2023Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimationcited by 2
  2. 2025Unsupervised Monocular 3D Keypoint Discovery from Multi-View Diffusion Priorscited by 0