mlsanityData to 7 Oct 2026

Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimation

arXiv 2004.03143 ↗First posted 7 Apr 2020cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

Monocular estimation of 3d human pose has attracted increased attention with the availability of large ground-truth motion capture datasets. However, the diversity of training data available is limited and it is not clear to what extent methods generalize outside the specific datasets they are trained on. In this work we carry out a systematic study of the diversity and biases present in specific datasets and its effect on cross-dataset generalization across a compendium of 5 pose datasets. We specifically focus on systematic differences in the distribution of camera viewpoints relative to a body-centered coordinate frame. Based on this observation, we propose an auxiliary task of predicting the camera viewpoint in addition to pose. We find that models trained to jointly predict viewpoint and pose systematically show significantly improved cross-dataset generalization.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 13; 2022: 9; 2023: 5; 2024: 3; 2025: 6.

36 papers.

Sort:

  1. 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 134
  2. 2021PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimationcited by 88
  3. 2021AFTer-UNet: Axial Fusion Transformer UNet for Medical Image Segmentationcited by 48
  4. 2024CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangementcited by 40
  5. 2021Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstructioncited by 39
  6. 2021TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimationcited by 32
  7. 2021AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generationcited by 32
  8. 2022HULC: 3D Human Motion Capture with Pose Manifold Sampling and Dense Contact Guidancecited by 29
  9. 2022PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimationcited by 27
  10. 2021PC-HMR: Pose Calibration for 3D Human Mesh Recovery from 2D Images/Videoscited by 25
  11. 2022Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localizationcited by 25
  12. 2022PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervisioncited by 25
24 more
  1. 2021Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptationcited by 24
  2. 2021Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimationcited by 19
  3. 2023Global Adaptation meets Local Generalization: Unsupervised Domain Adaptation for 3D Human Pose Estimationcited by 19
  4. 2021SSCAP: Self-supervised Co-occurrence Action Parsing for Unsupervised Temporal Action Segmentationcited by 15
  5. 2021MetaPose: Fast 3D Pose from Multiple Views without 3D Supervisioncited by 12
  6. 2022Identity-Aware Hand Mesh Estimation and Personalization from RGB Imagescited by 11
  7. 2022The Best of Both Worlds: Combining Model-based and Nonparametric Approaches for 3D Human Body Estimationcited by 8
  8. 2022Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledgecited by 6
  9. 2021PoseKernelLifter: Metric Lifting of 3D Human Pose using Soundcited by 4
  10. 2022PoseGU: 3D Human Pose Estimation with Novel Human Pose Generator and Unbiased Learningcited by 4
  11. 2021Learning Local Recurrent Models for Human Mesh Recoverycited by 3
  12. 2024Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimationcited by 2
  13. 2025PoseBench3D: A Cross-Dataset Analysis Framework for 3D Human Pose Estimation via Pose Lifting Networkscited by 2
  14. 2025PersPose: 3D Human Pose Estimation with Perspective Encoding and Perspective Rotationcited by 2
  15. 2022Decanus to Legatus: Synthetic training for 2D-3D human pose liftingcited by 1
  16. 2023SoloPose: One-Shot Kinematic 3D Human Pose Estimation with Video Data Augmentationcited by 1
  17. 2024ESCAPE: Energy-based Selective Adaptive Correction for Out-of-distribution 3D Human Pose Estimationcited by 1
  18. 2025Unsupervised Cross-Domain 3D Human Pose Estimation via Pseudo-Label-Guided Global Transformscited by 1
  19. 2023Distilling Token-Pruned Pose Transformer for 2D Human Pose Estimationcited by 0
  20. 2023Learning from Abstract Images: on the Importance of Occlusion in a Minimalist Encoding of Human Posescited by 0
  21. 2023Improved TokenPose with Sparsitycited by 0
  22. 2025Leveraging 2D Masked Reconstruction for Domain Adaptation of 3D Pose Estimationcited by 0
  23. 2025Toward Efficient Generalization in 3D Human Pose Estimation via a Canonical Domain Approachcited by 0
  24. 2025AugLift: Depth-Aware Input Reparameterization Improves Domain Generalization in 2D-to-3D Pose Liftingcited by 0