mlsanityData to 7 Oct 2026

Dynamic Graph Reasoning for Multi-person 3D Pose Estimation

arXiv 2207.11341 ↗First posted 22 Jul 2022cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Multi-person 3D pose estimation is a challenging task because of occlusion and depth ambiguity, especially in the cases of crowd scenes. To solve these problems, most existing methods explore modeling body context cues by enhancing feature representation with graph neural networks or adding structural constraints. However, these methods are not robust for their single-root formulation that decoding 3D poses from a root node with a pre-defined graph. In this paper, we propose GR-M3D, which models the Multi-person 3D pose estimation with dynamic Graph Reasoning. The decoding graph in GR-M3D is predicted instead of pre-defined. In particular, It firstly generates several data maps and enhances them with a scale and depth aware refinement module (SDAR). Then multiple root keypoints and dense decoding paths for each person are estimated from these data maps. Based on them, dynamic decoding graphs are built by assigning path weights to the decoding paths, while the path weights are inferred from those enhanced data maps. And this process is named dynamic graph reasoning (DGR). Finally, the 3D poses are decoded according to dynamic decoding graphs for each detected person. GR-M3D can adjust the structure of the decoding graph implicitly by adopting soft path weights according to input data, which makes the decoding graphs be adaptive to different input persons to the best extent and more capable of handling occlusion and depth ambiguity than previous methods. We empirically show that the proposed bottom-up approach even outperforms top-down methods and achieves state-of-the-art results on three 3D pose datasets.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 42 of its 55 references that are in the map. First posted on arXiv 22 Jul 2022.

Builds on

42 of 55 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  4. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  5. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  6. 2019Objects as Pointscited by 1,172
  7. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  8. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  9. 2017End-to-end Recovery of Human Shape and Posecited by 883
  10. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  11. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  12. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
30 more
  1. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  2. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 339
  3. 2017Integral Human Pose Regressioncited by 255
  4. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 220
  5. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  6. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  7. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  8. 2016Panoptic Studio: A Massively Multiview System for Social Interaction Capturecited by 173
  9. 2019Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Imagecited by 131
  10. 2017Compositional Human Pose Regressioncited by 124
  11. 2019PifPaf: Composite Fields for Human Pose Estimationcited by 120
  12. 2018Ordinal Depth Supervision for 3D Human Pose Estimationcited by 107
  13. 2019Single-Stage Multi-Person Pose Machinescited by 95
  14. 2020SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approachcited by 94
  15. 2020Detailed 2D-3D Joint Representation for Human-Object Interactioncited by 93
  16. 2018LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Imagescited by 88
  17. 20183D Human Pose Estimation in the Wild by Adversarial Learningcited by 86
  18. 2021Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flowscited by 84
  19. 20163D Human Pose Estimation from a Single Image via Distance Matrix Regressioncited by 73
  20. 2020Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimationcited by 57
  21. 2020SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimationcited by 52
  22. 2019DirectPose: Direct End-to-End Multi-Person Pose Estimationcited by 49
  23. 2018MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Networkcited by 47
  24. 2020HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimationcited by 44
  25. 2021Context Modeling in 3D Human Pose Estimation: A Unified Perspectivecited by 37
  26. 2020Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimationcited by 36
  27. 2017Generating Multiple Diverse Hypotheses for Human 3D Pose Consistent with 2D Joint Detectionscited by 30
  28. 2017Deep Multitask Architecture for Integrated 2D and 3D Human Sensingcited by 21
  29. 2019Multi-Person 3D Human Pose Estimation from Monocular Imagescited by 19
  30. 2021Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networkscited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 3; 2025: 1; 2026: 1.

9 papers.

  1. 2024Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shotcited by 98
  2. 2023PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformerscited by 31
  3. 2024SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokenscited by 15
  4. 2022Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledgecited by 6
  5. 2023Unlabeled Imperfect Demonstrations in Adversarial Imitation Learningcited by 3
  6. 2024Leveraging Anthropometric Measurements to Improve Human Mesh Estimation and Ensure Consistent Body Shapescited by 2
  7. 2023MM-NeRF: Multimodal-Guided 3D Multi-Style Transfer of Neural Radiance Fieldcited by 1
  8. 2025Systematic Comparison of Projection Methods for Monocular 3D Human Pose Estimation on Fisheye Imagescited by 1
  9. 2026Multi-HMR 2: Multi-Person Camera-Centric Human Detection, Mesh Recovery and Trackingcited by 1