mlsanityData to 7 Oct 2026

Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation

arXiv 1804.01110 ↗First posted 3 Apr 2018cs.CV cs.AIcited by 73

Not on the map. Why?

Abstract (arXiv)

Modern 3D human pose estimation techniques rely on deep networks, which require large amounts of training data. While weakly-supervised methods require less supervision, by utilizing 2D poses or multi-view imagery without annotations, they still need a sufficiently large set of samples with 3D annotations for learning to succeed. In this paper, we propose to overcome this problem by learning a geometry-aware body representation from multi-view images without annotations. To this end, we use an encoder-decoder that predicts an image from one viewpoint given an image from another viewpoint. Because this representation encodes 3D geometry, using it in a semi-supervised setting makes it easier to learn a mapping from it to 3D human pose. As evidenced by our experiments, our approach significantly outperforms fully-supervised methods given the same amount of labeled data, and improves over other semi-supervised methods while using as little as 1% of the labeled data.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 23; 2023: 13; 2024: 8; 2025: 3; 2026: 1.

73 papers.

Sort:

By area:

  1. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  2. 2021A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Posecited by 233
  3. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  4. 2021PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimationcited by 88
  5. 2023GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformerscited by 75
  6. 2021THUNDR: Transformer-based 3D HUmaN Reconstruction with Markerscited by 50
  7. 2022Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formatscited by 50
  8. 2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 49
  9. 2022Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformerscited by 33
  10. 2022Equivariant Point Cloud Analysis via Learning Orientations for Message Passingcited by 32
  11. 2024Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Modelscited by 30
  12. 2021AcinoSet: A 3D Pose Estimation Dataset and Baseline Models for Cheetahs in the Wildcited by 29
38 more
  1. 2021HSPACE: Synthetic Parametric Humans Animated in Complex Environmentscited by 29
  2. 2022LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypointscited by 27
  3. 2022Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessmentcited by 25
  4. 2022Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimationcited by 25
  5. 2022PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervisioncited by 25
  6. 2022Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDARcited by 23
  7. 2021BodyPressure -- Inferring Body Pose and Contact Pressure from a Depth Imagecited by 20
  8. 2021Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detectioncited by 20
  9. 2021Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfercited by 20
  10. 2023Vision-Based Human Pose Estimation via Deep Learning: A Surveycited by 20
  11. 2021GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generationcited by 19
  12. 2022MoCapDeform: Monocular 3D Human Motion Capture in Deformable Scenescited by 18
  13. 2022AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypointscited by 17
  14. 2022Contrastive Representation Learning for Gaze Estimationcited by 14
  15. 2021MetaPose: Fast 3D Pose from Multiple Views without 3D Supervisioncited by 12
  16. 2021Self-Supervised 3D Human Pose Estimation with Multiple-View Geometrycited by 10
  17. 2022On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimationcited by 10
  18. 2022Self-supervised Human Mesh Recovery with Cross-Representation Alignmentcited by 9
  19. 2022Progressive Multi-view Human Mesh Recovery with Self-Supervisioncited by 9
  20. 2024Markerless Multi-view 3D Human Pose Estimation: a surveycited by 9
  21. 2021Unsupervised Novel View Synthesis from a Single Imagecited by 8
  22. 2023Self-supervised 3D Human Pose Estimation from a Single Imagecited by 8
  23. 2023Rethinking Self-Supervised Visual Representation Learning in Pre-training for 3D Human Pose and Shape Estimationcited by 7
  24. 2023Unsupervised 3D Pose Estimation with Non-Rigid Structure-from-Motion Modelingcited by 7
  25. 2022Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimationcited by 6
  26. 2022A Light Touch Approach to Teaching Transformers Multi-view Geometrycited by 6
  27. 2023Few-shot Geometry-Aware Keypoint Localizationcited by 6
  28. 2021Semi-supervised Viewpoint Estimation with Geometry-aware Conditional Generationcited by 5
  29. 2022Enhancing Egocentric 3D Pose Estimation with Third Person Viewscited by 5
  30. 2022TUSK: Task-Agnostic Unsupervised Keypointscited by 5
  31. 2023Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Modelscited by 5
  32. 2021PoseKernelLifter: Metric Lifting of 3D Human Pose using Soundcited by 4
  33. 2022Estimating Pose from Pressure Data for Smart Beds with Deep Image-based Pose Estimatorscited by 4
  34. 2021Heuristic Weakly Supervised 3D Human Pose Estimationcited by 3
  35. 2021SVMAC: Unsupervised 3D Human Pose Estimation from a Single Image with Single-view-multi-angle Consistencycited by 3
  36. 2021Unsupervised View-Invariant Human Posture Representationcited by 3
  37. 2022ViewNet: Unsupervised Viewpoint Estimation from Conditional Generationcited by 3
  38. 2021Disentangling Geometric Deformation Spaces in Generative Latent Shape Modelscited by 2

50 most cited of 73 All 73 (JSON)