mlsanityData to 14 Oct 2026

Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation

arXiv 2203.07697 ↗First posted 15 Mar 2022cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

In this paper, we present a novel Distribution-Aware Single-stage (DAS) model for tackling the challenging multi-person 3D pose estimation problem. Different from existing top-down and bottom-up methods, the proposed DAS model simultaneously localizes person positions and their corresponding body joints in the 3D camera space in a one-pass manner. This leads to a simplified pipeline with enhanced efficiency. In addition, DAS learns the true distribution of body joints for the regression of their positions, rather than making a simple Laplacian or Gaussian assumption as previous works. This provides valuable priors for model prediction and thus boosts the regression-based scheme to achieve competitive performance with volumetric-base ones. Moreover, DAS exploits a recursive update strategy for progressively approaching to regression target, alleviating the optimization difficulty and further lifting the regression performance. DAS is implemented with a fully Convolutional Neural Network and end-to-end learnable. Comprehensive experiments on benchmarks CMU Panoptic and MuPoTS-3D demonstrate the superior efficiency of the proposed DAS model, specifically 1.5x speedup over previous best model, and its stat-of-the-art accuracy for multi-person 3D pose estimation.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 36 of its 50 references that are in the map. First posted on arXiv 15 Mar 2022.

Builds on

36 of 50 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  5. 2015Variational Inference with Normalizing Flowscited by 2,170
  6. 2016Density estimation using Real NVPcited by 2,042
  7. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  8. 2019Objects as Pointscited by 1,175
  9. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  10. 2014NICE: Non-linear Independent Components Estimationcited by 1,058
  11. 2017Focal Loss for Dense Object Detectioncited by 752
  12. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
24 more
  1. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  2. 2017Integral Human Pose Regressioncited by 256
  3. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
  4. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  5. 2021Probabilistic Modeling for Human Mesh Recoverycited by 153
  6. 2019Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Imagecited by 132
  7. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  8. 2017Compositional Human Pose Regressioncited by 124
  9. 2019Single-Stage Multi-Person Pose Machinescited by 95
  10. 2020Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flowscited by 94
  11. 2018LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Imagescited by 88
  12. 2021Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flowscited by 85
  13. 2019XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Cameracited by 68
  14. 2021Direct Multi-view Multi-person 3D Pose Estimationcited by 64
  15. 2019Rethinking on Multi-Stage Networks for Human Pose Estimationcited by 58
  16. 2020Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimationcited by 57
  17. 2020SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimationcited by 52
  18. 20203D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Datacited by 50
  19. 2021Body Meshes as Pointscited by 45
  20. 2020HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimationcited by 44
  21. 2020Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimationcited by 36
  22. 2017Deep Multitask Architecture for Integrated 2D and 3D Human Sensingcited by 21
  23. 2020HDNet: Human Depth Estimation for Multi-Person Camera-Space Localizationcited by 20
  24. 2018Vision-based Pose Estimation for Augmented Reality : A Comparison Studycited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 5; 2024: 0; 2025: 0; 2026: 2.

9 papers.

  1. 2023GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Videocited by 47
  2. 2023POCO: 3D Pose and Shape Estimation with Confidencecited by 21
  3. 2023Reconstructing Groups of People with Hypergraph Relational Reasoningcited by 18
  4. 2022Snipper: A Spatiotemporal Transformer for Simultaneous Multi-Person 3D Pose Estimation Tracking and Forecasting on a Video Snippetcited by 6
  5. 2022IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimationcited by 6
  6. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  7. 2023Intelligent Knee Sleeves: A Real-time Multimodal Dataset for 3D Lower Body Motion Estimation Using Smart Textilecited by 1
  8. 2026On the Role of Rotation Equivariance in Monocular 2D-to-3D Human Pose Liftingcited by 0
  9. 2026Efficient Online 3D Multi-Camera Multi-Object Tracking and Pose Estimationcited by 0