mlsanityData to 7 Oct 2026

Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image

arXiv 1907.11346 ↗First posted 26 Jul 2019cs.CVcited by 131

Not on the map. Why?

Abstract (arXiv)

Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case. In this work, we firstly propose a fully learning-based, camera distance-aware top-down approach for 3D multi-person pose estimation from a single RGB image. The pipeline of the proposed system consists of human detection, absolute 3D human root localization, and root-relative 3D single-person pose estimation modules. Our system achieves comparable results with the state-of-the-art 3D single-person pose estimation models without any groundtruth information and significantly outperforms previous 3D multi-person pose estimation methods on publicly available datasets. The code is available in https://github.com/mks0601/3DMPPE_ROOTNET_RELEASE , https://github.com/mks0601/3DMPPE_POSENET_RELEASE.

Key facts. Cited by 131 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 34; 2022: 35; 2023: 26; 2024: 20; 2025: 8; 2026: 8.

131 papers.

Sort:

By area:

  1. 2021AGORA: Avatars in Geography Optimized for Regression Analysiscited by 203
  2. 2022MotionBERT: A Unified Perspective on Learning Human Motion Representationscited by 188
  3. 2021GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Camerascited by 151
  4. 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 141
  5. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  6. 2021Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimationcited by 122
  7. 2021Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimationcited by 101
  8. 2021PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimationcited by 88
  9. 2021Multi-Person Extreme Motion Predictioncited by 74
  10. 2021Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenescited by 64
  11. 2021Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registrationcited by 59
  12. 2024HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environmentcited by 52
38 more
  1. 2022Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formatscited by 50
  2. 2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 49
  3. 2022UmeTrack: Unified multi-view end-to-end hand tracking for VRcited by 48
  4. 2023HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recoverycited by 48
  5. 2021Reconstructing 3D Human Pose by Watching Humans in the Mirrorcited by 47
  6. 2021Body Meshes as Pointscited by 45
  7. 2023Human Pose as Compositional Tokenscited by 45
  8. 2021Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentationcited by 40
  9. 2022D&D: Learning Human Dynamics from Dynamic Cameracited by 39
  10. 2021Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Imagescited by 38
  11. 2023PACE: Human and Camera Motion Estimation from in-the-wild Videoscited by 33
  12. 2024KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimationcited by 33
  13. 2023PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformerscited by 31
  14. 2021Gravity-Aware Monocular 3D Human-Object Reconstructioncited by 30
  15. 2022Embodied Scene-aware Human Pose Estimationcited by 28
  16. 2021PC-HMR: Pose Calibration for 3D Human Mesh Recovery from 2D Images/Videoscited by 25
  17. 2022Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localizationcited by 25
  18. 2024PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarioscited by 24
  19. 2022H3WB: Human3.6M 3D WholeBody Dataset and Benchmarkcited by 23
  20. 2022Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDARcited by 23
  21. 2021PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimationcited by 22
  22. 2022HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Drivingcited by 22
  23. 2023Scene-Aware 3D Multi-Human Motion Capture from a Single Cameracited by 19
  24. 2023Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimationcited by 19
  25. 2021Recognizing Actions in Videos from Unseen Viewpointscited by 18
  26. 2022MoCapDeform: Monocular 3D Human Motion Capture in Deformable Scenescited by 18
  27. 2022PLIKS: A Pseudo-Linear Inverse Kinematic Solver for 3D Human Body Estimationcited by 18
  28. 2023Reconstructing Groups of People with Hypergraph Relational Reasoningcited by 18
  29. 2024LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Modelcited by 17
  30. 2021Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networkscited by 16
  31. 2022Learning Visibility for Robust Dense Human Body Estimationcited by 15
  32. 2024COIN: Control-Inpainting Diffusion Prior for Human and Camera Motion Estimationcited by 15
  33. 2021MoCaNet: Motion Retargeting in-the-wild via Canonicalization Networkscited by 13
  34. 2022Dual networks based 3D Multi-Person Pose Estimation from Monocular Videocited by 13
  35. 2021Part-Aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and Trackingcited by 12
  36. 2023Crowd3D: Towards Hundreds of People Reconstruction from a Single Imagecited by 12
  37. 2023Unlocking the Emotional World of Visual Media: An Overview of the Science, Research, and Impact of Understanding Emotioncited by 12
  38. 2023LiDAR-HMR: 3D Human Mesh Recovery from LiDARcited by 12

50 most cited of 131 All 131 (JSON)