mlsanityData to 7 Oct 2026

SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation

arXiv 2008.11469 ↗First posted 26 Aug 2020cs.CVcited by 52

Not on the map. Why?

Abstract (arXiv)

Recovering multi-person 3D poses with absolute scales from a single RGB image is a challenging problem due to the inherent depth and scale ambiguity from a single view. Addressing this ambiguity requires to aggregate various cues over the entire image, such as body sizes, scene layouts, and inter-person relationships. However, most previous methods adopt a top-down scheme that first performs 2D pose detection and then regresses the 3D pose and scale for each detected person individually, ignoring global contextual cues. In this paper, we propose a novel system that first regresses a set of 2.5D representations of body parts and then reconstructs the 3D absolute poses based on these 2.5D representations with a depth-aware part association algorithm. Such a single-shot bottom-up scheme allows the system to better learn and reason about the inter-person depth relationship, improving both 3D and 2D pose estimation. The experiments demonstrate that the proposed approach achieves the state-of-the-art performance on the CMU Panoptic and MuPoTS-3D datasets and is applicable to in-the-wild videos.

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 17; 2023: 14; 2024: 8; 2025: 2; 2026: 3.

52 papers.

Sort:

By area:

  1. 2021GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Camerascited by 151
  2. 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 141
  3. 2024Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shotcited by 98
  4. 2021Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenescited by 64
  5. 2024HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environmentcited by 52
  6. 2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 49
  7. 2021Reconstructing 3D Human Pose by Watching Humans in the Mirrorcited by 47
  8. 2023SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environmentscited by 47
  9. 2021Body Meshes as Pointscited by 45
  10. 2023PACE: Human and Camera Motion Estimation from in-the-wild Videoscited by 33
  11. 2023PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformerscited by 31
  12. 2022Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localizationcited by 25
38 more
  1. 2021Shape-aware Multi-Person Pose Estimation from Multi-View Imagescited by 24
  2. 2022Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDARcited by 23
  3. 2023Vision-Based Human Pose Estimation via Deep Learning: A Surveycited by 20
  4. 2023Scene-Aware 3D Multi-Human Motion Capture from a Single Cameracited by 19
  5. 2023Reconstructing Groups of People with Hypergraph Relational Reasoningcited by 18
  6. 2023Fusing Monocular Images and Sparse IMU Signals for Real-time Human Motion Capturecited by 17
  7. 2021Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networkscited by 16
  8. 2024COIN: Control-Inpainting Diffusion Prior for Human and Camera Motion Estimationcited by 15
  9. 2022Dual networks based 3D Multi-Person Pose Estimation from Monocular Videocited by 13
  10. 2023Learning Human Mesh Recovery in 3D Scenescited by 13
  11. 2023Crowd3D: Towards Hundreds of People Reconstruction from a Single Imagecited by 12
  12. 2023LiDAR-HMR: 3D Human Mesh Recovery from LiDARcited by 12
  13. 2023Towards Robust and Smooth 3D Multi-Person Pose Estimation from Monocular Videos in the Wildcited by 11
  14. 2024Deep learning for 3D human pose estimation and mesh recovery: A surveycited by 11
  15. 2022VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Datacited by 10
  16. 2022Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimationcited by 10
  17. 2022Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimationcited by 9
  18. 2022Dynamic Graph Reasoning for Multi-person 3D Pose Estimationcited by 9
  19. 2024Reconstructing Close Human Interactions from Multiple Viewscited by 7
  20. 2022NIMBLE: A Non-rigid Hand Model with Bones and Musclescited by 6
  21. 2022Snipper: A Spatiotemporal Transformer for Simultaneous Multi-Person 3D Pose Estimation Tracking and Forecasting on a Video Snippetcited by 6
  22. 2022IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimationcited by 6
  23. 2022AdaptivePose++: A Powerful Single-Stage Network for Multi-Person Pose Regressioncited by 6
  24. 2022Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledgecited by 6
  25. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  26. 2023Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Modelscited by 5
  27. 2024A Medical Low-Back Pain Physical Rehabilitation Dataset for Human Body Movement Analysiscited by 5
  28. 2022Permutation-Invariant Relational Network for Multi-person 3D Pose Estimationcited by 3
  29. 2022MUG: Multi-human Graph Network for 3D Mesh Reconstruction from 2D Posecited by 3
  30. 2025DyCrowd: Towards Dynamic Crowd Reconstruction from a Large-scene Videocited by 3
  31. 2024RCR: Robust Crowd Reconstruction with Upright Space from a Single Large-scene Imagecited by 2
  32. 2022Diverse Dance Synthesis via Keyframes with Transformer Controllerscited by 1
  33. 2025Systematic Comparison of Projection Methods for Monocular 3D Human Pose Estimation on Fisheye Imagescited by 1
  34. 2022Unified Simulation, Perception, and Generation of Human Behaviorcited by 0
  35. 2022Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimationcited by 0
  36. 2023Probabilistic 3d regression with projected huber distributioncited by 0
  37. 2024Map-Free Visual Relocalization Enhanced by Instance Knowledge and Depth Knowledgecited by 0
  38. 2026Garment Inertial Denoiser (GID): Endowing Accurate Motion Capture via Loose IMU Denoisercited by 0

50 most cited of 52 All 52 (JSON)