mlsanityData to 7 Oct 2026

UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues

arXiv 2404.14634 ↗First posted 23 Apr 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

We introduce UPose3D, a novel approach for multi-view 3D human pose estimation, addressing challenges in accuracy and scalability. Our method advances existing pose estimation frameworks by improving robustness and flexibility without requiring direct 3D annotations. At the core of our method, a pose compiler module refines predictions from a 2D keypoints estimator that operates on a single image by leveraging temporal and cross-view information. Our novel cross-view fusion strategy is scalable to any number of cameras, while our synthetic data generation strategy ensures generalization across diverse actors, scenes, and viewpoints. Finally, UPose3D leverages the prediction uncertainty of both the 2D keypoint estimator and the pose compiler module. This provides robustness to outliers and noisy data, resulting in state-of-the-art performance in out-of-distribution settings. In addition, for in-distribution settings, UPose3D yields performance rivalling methods that rely on 3D annotated data while being the state-of-the-art among methods relying only on 2D supervision.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 53 of its 72 references that are in the map. First posted on arXiv 23 Apr 2024.

Builds on

53 of 72 references.

References · 53

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2015Variational Inference with Normalizing Flowscited by 2,161
  6. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  7. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  8. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  9. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  10. 2020PCT: Point cloud transformercited by 730
  11. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  12. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
38 more
  1. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  2. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  3. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  4. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
  5. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 319
  6. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  7. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 237
  8. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
  9. 2020Whole-Body Human Pose Estimation in the Wildcited by 178
  10. 2022Capturing and Inferring Dense Full-Body Human-Scene Contactcited by 176
  11. 2019Learnable Triangulation of Human Posecited by 160
  12. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  13. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  14. 2020Epipolar Transformerscited by 117
  15. 2017Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approachcited by 114
  16. 20233D Human Pose Estimation via Intuitive Physicscited by 100
  17. 2019Self-Supervised Learning of 3D Human Pose using Multi-view Geometrycited by 98
  18. 2019Cross View Fusion for 3D Human Pose Estimationcited by 90
  19. 2018Learning Monocular 3D Human Pose Estimation from Multi-view Imagescited by 70
  20. 2022Benchmarking and Analyzing Point Cloud Classification under Corruptionscited by 70
  21. 2021SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimationcited by 68
  22. 2020CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wildcited by 65
  23. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion modelscited by 65
  24. 2020NeuralAnnot: Neural Annotator for 3D Human Mesh Training Setscited by 62
  25. 2020Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representationcited by 57
  26. 2023HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recoverycited by 48
  27. 2020AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wildcited by 40
  28. 2021TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimationcited by 32
  29. 2022Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimationcited by 25
  30. 2021Generalizable Human Pose Triangulationcited by 24
  31. 2023POCO: 3D Pose and Shape Estimation with Confidencecited by 20
  32. 2021Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimationcited by 19
  33. 2021HUMBI: A Large Multiview Dataset of Human Body Expressions and Benchmark Challengecited by 17
  34. 2023Learning Human Mesh Recovery in 3D Scenescited by 13
  35. 2021MetaPose: Fast 3D Pose from Multiple Views without 3D Supervisioncited by 12
  36. 2021FLEX: Extrinsic Parameters-free Multi-view 3D Human Motion Reconstructioncited by 11
  37. 2022BKinD-3D: Self-Supervised 3D Keypoint Discovery from Multi-View Videoscited by 10
  38. 2022Progressive Multi-view Human Mesh Recovery with Self-Supervisioncited by 9

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 4.

6 papers.

  1. 2024CondiMen: Conditional Multi-Person Mesh Recoverycited by 5
  2. 2026Unconstrained Multi-view Human Pose Estimation with Algebraic Priorscited by 1
  3. 2025SkelSplat: Robust Multi-view 3D Human Pose Estimation with Differentiable Gaussian Renderingcited by 0
  4. 2026Vision-Based Safe Human-Robot Collaboration with Uncertainty Guaranteescited by 0
  5. 2026UST-Hand: An Uncertainty-aware Spatiotemporal Point Cloud Interaction Network for 3D Self-supervised Hand Pose Estimationcited by 0
  6. 2026MEOM: Multi-View Expected-OKS Maximization for Human Pose Triangulationcited by 0