mlsanityData to 7 Oct 2026

Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection

arXiv 2207.10955 ↗First posted 22 Jul 2022cs.CVcited by 39

Not on the map. Why?

Abstract (arXiv)

While the voxel-based methods have achieved promising results for multi-person 3D pose estimation from multi-cameras, they suffer from heavy computation burdens, especially for large scenes. We present Faster VoxelPose to address the challenge by re-projecting the feature volume to the three two-dimensional coordinate planes and estimating X, Y, Z coordinates from them separately. To that end, we first localize each person by a 3D bounding box by estimating a 2D box and its height based on the volume features projected to the xy-plane and z-axis, respectively. Then for each person, we estimate partial joint coordinates from the three coordinate planes separately which are then fused to obtain the final 3D pose. The method is free from costly 3D-CNNs and improves the speed of VoxelPose by ten times and meanwhile achieves competitive accuracy as the state-of-the-art methods, proving its potential in real-time applications.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 39 of its 60 references that are in the map. First posted on arXiv 22 Jul 2022.

Builds on

39 of 60 references.

References · 39

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  3. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  4. 2019Objects as Pointscited by 1,172
  5. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  6. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  7. 20213D Human Pose Estimation with Spatial and Temporal Transformerscited by 271
  8. 2019Learnable Triangulation of Human Posecited by 160
  9. 2021ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detectioncited by 157
  10. 2020Epipolar Transformerscited by 117
  11. 2019Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Networkcited by 92
  12. 2019Cross View Fusion for 3D Human Pose Estimationcited by 90
27 more
  1. 2019Fast and Robust Multi-Person 3D Pose Estimation from Multiple Viewscited by 83
  2. 2019Monocular 3D Human Pose Estimation by Generation and Ordinal Rankingcited by 76
  3. 2018Fast Human Pose Estimationcited by 68
  4. 2018Photo Wake-Up: 3D Character Animation from a Single Photocited by 60
  5. 2020Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representationcited by 57
  6. 2021Online Knowledge Distillation for Efficient Pose Estimationcited by 55
  7. 2019HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimationcited by 50
  8. 20204D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Camerascited by 49
  9. 2017Harvesting Multiple Views for Marker-less 3D Human Pose Annotationscited by 48
  10. 2020AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wildcited by 40
  11. 2021VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wildcited by 39
  12. 2021Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereocited by 38
  13. 2021Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Imagescited by 38
  14. 2021Context Modeling in 3D Human Pose Estimation: A Unified Perspectivecited by 37
  15. 2020Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimationcited by 36
  16. 2020Motion Capture from Internet Videoscited by 33
  17. 2021Voxel-based Network for Shape Completion by Leveraging Edge Generationcited by 32
  18. 2020Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric Approachcited by 27
  19. 2015Detecting events and key actors in multi-person videoscited by 26
  20. 2021ViPNAS: Efficient Video Pose Estimation via Neural Architecture Searchcited by 26
  21. 2020Reconstructing NBA Playerscited by 24
  22. 2014Robust Estimation of 3D Human Poses from a Single Imagecited by 23
  23. 2021Voxel-based 3D Detection and Reconstruction of Multiple Objects from a Single Imagecited by 20
  24. 2020Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networkscited by 19
  25. 2021Real-Time Multi-View 3D Human Pose Estimation using Semantic Feedback to Smart Edge Sensorscited by 16
  26. 2021VIN: Voxel-based Implicit Network for Joint 3D Object Detection and Segmentation for Lidarscited by 6
  27. 2021Towards Fast and Accurate Multi-Person Pose Estimation on Mobile Devicescited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 11; 2024: 9; 2025: 10; 2026: 7.

39 papers.

Sort:

By area:

  1. 2023Human Motion Generation: A Surveycited by 95
  2. 20233D Human Mesh Estimation from Virtual Markerscited by 44
  3. 2022Scene-aware Egocentric 3D Human Pose Estimationcited by 30
  4. 2023HDFormer: High-order Directed Transformer for 3D Human Pose Estimationcited by 23
  5. 2023TEMPO: Efficient Multi-View Pose Estimation, Tracking, and Forecastingcited by 22
  6. 2023Multiple View Geometry Transformers for 3D Human Pose Estimationcited by 19
  7. 2024SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokenscited by 15
  8. 2023Markerless human pose estimation for biomedical applications: a surveycited by 13
  9. 2025WorldPose: A World Cup Dataset for Global 3D Human Pose Estimationcited by 13
  10. 2024Markerless Multi-view 3D Human Pose Estimation: a surveycited by 9
  11. 2025MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimationcited by 9
  12. 2023Social Motion Prediction with Cognitive Hierarchiescited by 8
27 more
  1. 2024Reconstructing Close Human Interactions from Multiple Viewscited by 7
  2. 2024AvatarPose: Avatar-guided 3D Pose Estimation of Close Human Interaction from Sparse Multi-view Videoscited by 7
  3. 2023A Unified Multi-view Multi-person Tracking Frameworkcited by 5
  4. 2024CondiMen: Conditional Multi-Person Mesh Recoverycited by 5
  5. 2024Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimationcited by 4
  6. 2025Kineo: Calibration-Free Metric Motion Capture From Sparse RGB Camerascited by 4
  7. 2024VoxelKeypointFusion: Generalizable Multi-View Multi-Person Pose Estimationcited by 3
  8. 2022Multi-person 3D pose estimation from unlabelled datacited by 2
  9. 2024Sports Analysis and VR Viewing System Based on Player Tracking and Pose Estimation with Multimodal and Multiview Sensorscited by 2
  10. 2025Every Angle Is Worth A Second Glance: Mining Kinematic Skeletal Structures from Multi-view Joint Cloudcited by 2
  11. 2025RapidPoseTriangulation: Multi-view Multi-person Whole-body Human Pose Triangulation in a Millisecondcited by 2
  12. 2023LiCamPose: Combining Multi-View LiDAR and RGB Cameras for Robust Single-timestamp 3D Human Pose Estimationcited by 1
  13. 2025SimpleDepthPose: Fast and Reliable Human Pose Estimation with RGBD-Imagescited by 1
  14. 2025P2P-Insole: Human Pose Estimation Using Foot Pressure Distribution and Motion Sensorscited by 1
  15. 2025Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forwardcited by 1
  16. 2026COMPOSE: Hypergraph Cover Optimization for Multi-view 3D Human Pose Estimationcited by 1
  17. 2026Unconstrained Multi-view Human Pose Estimation with Algebraic Priorscited by 1
  18. 2023Noise-in, Bias-out: Balanced and Real-time MoCap Solvingcited by 0
  19. 2023BundleMoCap: Efficient, Robust and Smooth Motion Capture from Sparse Multiview Videoscited by 0
  20. 2024Marker-free Human Gait Analysis using a Smart Edge Sensor Systemcited by 0
  21. 2025MAMMA: Markerless & Automatic Multi-Person Motion Action Capturecited by 0
  22. 2025Shape-aware Inertial Poser: Motion Tracking for Humans with Diverse Shapes Using Sparse Inertial Sensorscited by 0
  23. 2026RePose: A Real-Time 3D Human Pose Estimation and Biomechanical Analysis Framework for Rehabilitationcited by 0
  24. 2026Efficient Online 3D Multi-Camera Multi-Object Tracking and Pose Estimationcited by 0
  25. 2026Mesh-Aware Epipolar Matching for Multi-View Multi-Person 3D Pose Estimation in Basketballcited by 0
  26. 2026DisPOSE: Projected Polystochastic Diffusion for Self-Supervised Multi-View 3D Human Pose Estimationcited by 0
  27. 2026Beyond the Survey: A Systematic Empirical Study of Detection and Association in Visual MOTcited by 0