mlsanityData to 7 Oct 2026

Unsupervised Human Pose Estimation through Transforming Shape Templates

arXiv 2105.04154 ↗First posted 10 May 2021cs.CV cs.AIcited by 26

Not on the map. Why?

Abstract (arXiv)

Human pose estimation is a major computer vision problem with applications ranging from augmented reality and video capture to surveillance and movement tracking. In the medical context, the latter may be an important biomarker for neurological impairments in infants. Whilst many methods exist, their application has been limited by the need for well annotated large datasets and the inability to generalize to humans of different shapes and body compositions, e.g. children and infants. In this paper we present a novel method for learning pose estimators for human adults and infants in an unsupervised fashion. We approach this as a learnable template matching problem facilitated by deep feature extractors. Human-interpretable landmarks are estimated by transforming a template consisting of predefined body parts that are characterized by 2D Gaussian distributions. Enforcing a connectivity prior guides our model to meaningful human shape representations. We demonstrate the effectiveness of our approach on two different datasets including adults and infants.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 36 of its 64 references that are in the map. First posted on arXiv 10 May 2021.

Builds on

36 of 64 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  4. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  5. 2017End-to-end Recovery of Human Shape and Posecited by 883
  6. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  7. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  8. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  9. 2016Convolutional Pose Machinescited by 325
  10. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  11. 2014Efficient Object Localization Using Convolutional Networkscited by 226
  12. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
24 more
  1. 2019GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstructioncited by 150
  2. 2017Convolutional neural network architecture for geometric matchingcited by 138
  3. 2017Morphable Face Models - An Open Frameworkcited by 138
  4. 2014Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimationcited by 129
  5. 2015Human Pose Estimation with Iterative Error Feedbackcited by 121
  6. 2018Unsupervised Learning of Object Landmarks through Conditional Image Generationcited by 113
  7. 20163D Human Pose Estimation = 2D Pose Estimation + Matchingcited by 112
  8. 2017SfSNet: Learning Shape, Reflectance and Illuminance of Faces in the Wildcited by 110
  9. 2016DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Modelcited by 96
  10. 20183D Human Pose Estimation in the Wild by Adversarial Learningcited by 86
  11. 2018Unsupervised Discovery of Object Landmarks as Structural Representationscited by 73
  12. 2019Unsupervised Part-Based Disentangling of Object Shape and Appearancecited by 67
  13. 2018Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearancecited by 58
  14. 2015Flowing ConvNets for Human Pose Estimation in Videoscited by 55
  15. 2016Human pose estimation via Convolutional Part Heatmap Regressioncited by 51
  16. 20193D Guided Fine-Grained Face Manipulationcited by 45
  17. 2018Self-supervised learning of a facial attribute embedding from videocited by 44
  18. 2020Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesiscited by 44
  19. 2019Unsupervised Learning of Landmarks by Descriptor Vector Exchangecited by 39
  20. 2016Recurrent Human Pose Estimationcited by 27
  21. 2017Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervisioncited by 27
  22. 2016WarpNet: Weakly Supervised Matching for Single-view Reconstructioncited by 22
  23. 2019Automatic Posture and Movement Tracking of Infants with Wearable Movement Sensorscited by 10
  24. 2017An Adversarial Neuro-Tensorial Approach For Learning Disentangled Representationscited by 8

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 8; 2023: 8; 2024: 4; 2025: 2.

26 papers.

Sort:

By area:

  1. 2021Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objectscited by 50
  2. 2023Human Pose as Compositional Tokenscited by 45
  3. 2023DiffPose: SpatioTemporal Diffusion Model for Video-Based Human Pose Estimationcited by 36
  4. 2022Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimationcited by 24
  5. 2021Self-Supervised Keypoint Discovery in Behavioral Videoscited by 23
  6. 20222D Human Pose Estimation: A Surveycited by 21
  7. 2022AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypointscited by 17
  8. 2023Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Videocited by 17
  9. 2023Unsupervised Keypoints from Pretrained Diffusion Modelscited by 15
  10. 20233D Human Keypoints Estimation From Point Clouds in the Wild Without Human Labelscited by 9
  11. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  12. 2022A survey of top-down approaches for human pose estimationcited by 3
14 more
  1. 2024Pose Prior Learner: Unsupervised Categorical Prior Learning for Pose Estimationcited by 3
  2. 2025SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videoscited by 3
  3. 2022Neural Marionette: Unsupervised Learning of Motion Skeleton and Latent Dynamics from Volumetric Videocited by 2
  4. 2022Self-Supervised 3D Human Pose Estimation in Static Video Via Neural Renderingcited by 2
  5. 2022Unsupervised 3D Keypoint Discovery with Multi-View Geometrycited by 2
  6. 2023Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimationcited by 2
  7. 20213D Human Pose Estimation Based on 2D-3D Consistency with Synchronized Adversarial Trainingcited by 1
  8. 2021Bottom-up approaches for multi-person pose estimation and it's applications: A brief reviewcited by 1
  9. 2022Decanus to Legatus: Synthetic training for 2D-3D human pose liftingcited by 1
  10. 2023Efficient, Self-Supervised Human Pose Estimation with Inductive Prior Tuningcited by 1
  11. 2024Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimationcited by 0
  12. 2024Depth-Guided Self-Supervised Human Keypoint Detection via Cross-Modal Distillationcited by 0
  13. 2024X as Supervision: Contending with Depth Ambiguity in Unsupervised Monocular 3D Pose Estimationcited by 0
  14. 2025Multi-Grained Feature Pruning for Video-Based Human Pose Estimationcited by 0