mlsanityData to 7 Oct 2026

Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation

arXiv 2312.07051 ↗First posted 12 Dec 2023cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Automatic estimation of 3D human pose from monocular RGB images is a challenging and unsolved problem in computer vision. In a supervised manner, approaches heavily rely on laborious annotations and present hampered generalization ability due to the limited diversity of 3D pose datasets. To address these challenges, we propose a unified framework that leverages mask as supervision for unsupervised 3D pose estimation. With general unsupervised segmentation algorithms, the proposed model employs skeleton and physique representations that exploit accurate pose information from coarse to fine. Compared with previous unsupervised approaches, we organize the human skeleton in a fully unsupervised way which enables the processing of annotation-free data and provides ready-to-use estimation results. Comprehensive experiments demonstrate our state-of-the-art pose estimation performance on Human3.6M and MPI-INF-3DHP datasets. Further experiments on in-the-wild datasets also illustrate the capability to access more data to boost our model. Code will be available at https://github.com/Charrrrrlie/Mask-as-Supervision.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 34 of its 57 references that are in the map. First posted on arXiv 12 Dec 2023.

Builds on

34 of 57 references.

References · 34

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2023Segment Anythingcited by 8,158
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2018Group Normalizationcited by 1,514
  5. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  6. 2020First Order Motion Model for Image Animationcited by 698
  7. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  8. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  9. 2017Integral Human Pose Regressioncited by 255
  10. 2017Unsupervised Learning of Disentangled Representations from Videocited by 138
  11. 2018Unsupervised Learning of Object Landmarks through Conditional Image Generationcited by 113
  12. 2019Self-Supervised Learning of 3D Human Pose using Multi-view Geometrycited by 98
22 more
  1. 2019Unsupervised 3D Pose Estimation with Geometric Self-Supervisioncited by 95
  2. 2021PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimationcited by 88
  3. 2018Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoningcited by 79
  4. 2018Unsupervised Discovery of Object Landmarks as Structural Representationscited by 73
  5. 2019Unsupervised Part-Based Disentangling of Object Shape and Appearancecited by 67
  6. 2020CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wildcited by 65
  7. 2022TAX-Pose: Task-Specific Cross-Pose Estimation for Robot Manipulationcited by 47
  8. 2020Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesiscited by 44
  9. 2022Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motioncited by 42
  10. 2019Unsupervised Learning of Landmarks by Descriptor Vector Exchangecited by 39
  11. 2020Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimationcited by 26
  12. 2021Unsupervised Human Pose Estimation through Transforming Shape Templatescited by 26
  13. 2019Neural Scene Decomposition for Multi-Person Motion Capturecited by 21
  14. 2021Differentiable Drawing and Sketchingcited by 20
  15. 2022AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypointscited by 17
  16. 2023Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Groupingcited by 15
  17. 2022BKinD-3D: Self-Supervised 3D Keypoint Discovery from Multi-View Videoscited by 10
  18. 2022Fast and Robust Video-Based Exercise Classification via Body Pose Tracking and Scalable Multivariate Time Series Classifierscited by 8
  19. 2023Self-supervised 3D Human Pose Estimation from a Single Imagecited by 8
  20. 2020Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimationcited by 7
  21. 2023Few-shot Geometry-Aware Keypoint Localizationcited by 6
  22. 2022Unsupervised 3D Keypoint Discovery with Multi-View Geometrycited by 2

Built on by

Cited by year

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

2 papers.

  1. 2024X as Supervision: Contending with Depth Ambiguity in Unsupervised Monocular 3D Pose Estimationcited by 0
  2. 2025Unsupervised Monocular 3D Keypoint Discovery from Multi-View Diffusion Priorscited by 0