mlsanityData to 7 Oct 2026

Lifting 2D Human Pose to 3D with Domain Adapted 3D Body Concept

arXiv 2111.11969 ↗First posted 23 Nov 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Lifting the 2D human pose to the 3D pose is an important yet challenging task. Existing 3D pose estimation suffers from 1) the inherent ambiguity between the 2D and 3D data, and 2) the lack of well labeled 2D-3D pose pairs in the wild. Human beings are able to imagine the human 3D pose from a 2D image or a set of 2D body key-points with the least ambiguity, which should be attributed to the prior knowledge of the human body that we have acquired in our mind. Inspired by this, we propose a new framework that leverages the labeled 3D human poses to learn a 3D concept of the human body to reduce the ambiguity. To have consensus on the body concept from 2D pose, our key insight is to treat the 2D human pose and the 3D human pose as two different domains. By adapting the two domains, the body knowledge learned from 3D poses is applied to 2D poses and guides the 2D pose encoder to generate informative 3D "imagination" as embedding in pose lifting. Benefiting from the domain adaptation perspective, the proposed framework unifies the supervised and semi-supervised 3D pose estimation in a principled framework. Extensive experiments demonstrate that the proposed approach can achieve state-of-the-art performance on standard benchmarks. More importantly, it is validated that the explicitly learned 3D body concept effectively alleviates the 2D-3D ambiguity in 2D pose lifting, improves the generalization, and enables the network to exploit the abundant unlabeled 2D data.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 41 of its 56 references that are in the map. First posted on arXiv 23 Nov 2021.

Builds on

41 of 56 references.

References · 41

  1. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  2. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  3. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  4. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  5. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  6. 2017End-to-end Recovery of Human Shape and Posecited by 883
  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. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  10. 2016Convolutional Pose Machinescited by 325
  11. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  12. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 220
29 more
  1. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  2. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  3. 2019Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Imagecited by 131
  4. 2017Domain Adaptation for Visual Applications: A Comprehensive Surveycited by 127
  5. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 114
  6. 2019Self-Supervised Learning of 3D Human Pose using Multi-view Geometrycited by 98
  7. 2019Unsupervised 3D Pose Estimation with Geometric Self-Supervisioncited by 95
  8. 2019Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Networkcited by 92
  9. 2017Exploiting temporal information for 3D pose estimationcited by 89
  10. 2021PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimationcited by 88
  11. 20183D Human Pose Estimation in the Wild by Adversarial Learningcited by 86
  12. 2019RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimationcited by 85
  13. 2020Cascaded deep monocular 3D human pose estimation with evolutionary training datacited by 80
  14. 2019Monocular 3D Human Pose Estimation by Generation and Ordinal Rankingcited by 76
  15. 2019Open Compound Domain Adaptationcited by 76
  16. 20163D Human Pose Estimation from a Single Image via Distance Matrix Regressioncited by 73
  17. 2018Learning Monocular 3D Human Pose Estimation from Multi-view Imagescited by 70
  18. 2020Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wildcited by 66
  19. 2019HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimationcited by 50
  20. 2019In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representationscited by 48
  21. 2018Can 3D Pose be Learned from 2D Projections Alone?cited by 44
  22. 2020Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesiscited by 44
  23. 2016Structured Prediction of 3D Human Pose with Deep Neural Networkscited by 43
  24. 2021Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstructioncited by 39
  25. 2020Inference Stage Optimization for Cross-scenario 3D Human Pose Estimationcited by 35
  26. 2020Unsupervised 3D Human Pose Representation with Viewpoint and Pose Disentanglementcited by 32
  27. 2019Multiview-Consistent Semi-Supervised Learning for 3D Human Pose Estimationcited by 31
  28. 2018OriNet: A Fully Convolutional Network for 3D Human Pose Estimationcited by 28
  29. 2019Not All Parts Are Created Equal: 3D Pose Estimation by Modelling Bi-directional Dependencies of Body Partscited by 19

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2; 2025: 1.

4 papers.

  1. 2024FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Modelscited by 23
  2. 2023HopFIR: Hop-wise GraphFormer with Intragroup Joint Refinement for 3D Human Pose Estimationcited by 7
  3. 2024Di2Pose: Discrete Diffusion Model for Occluded 3D Human Pose Estimationcited by 2
  4. 2025PriorFormer: A Transformer for Real-time Monocular 3D Human Pose Estimation with Versatile Geometric Priorscited by 1