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

arXiv: https://arxiv.org/abs/2207.10955 · HTML: https://mlsanity.com/paper/2207.10955/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 60 references that are in the map.
- First posted on arXiv 22 Jul 2022.

## Builds on (most cited first, 30 of 39)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [3D human pose estimation in video with temporal convolutions and semi-supervised training](https://mlsanity.com/paper/1811.11742/) (2018)
- [RMPE: Regional Multi-person Pose Estimation](https://mlsanity.com/paper/1612.00137/) (2016)
- [3D Human Pose Estimation with Spatial and Temporal Transformers](https://mlsanity.com/paper/2103.10455/) (2021)
- [Learnable Triangulation of Human Pose](https://mlsanity.com/paper/1905.05754/) (2019)
- [ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection](https://mlsanity.com/paper/2106.01178/) (2021)
- [Epipolar Transformers](https://mlsanity.com/paper/2005.04551/) (2020)
- [Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network](https://mlsanity.com/paper/1904.05547/) (2019)
- [Cross View Fusion for 3D Human Pose Estimation](https://mlsanity.com/paper/1909.01203/) (2019)
- [Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views](https://mlsanity.com/paper/1901.04111/) (2019)
- [Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking](https://mlsanity.com/paper/1904.01324/) (2019)
- [Fast Human Pose Estimation](https://mlsanity.com/paper/1811.05419/) (2018)
- [Photo Wake-Up: 3D Character Animation from a Single Photo](https://mlsanity.com/paper/1812.02246/) (2018)
- [Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation](https://mlsanity.com/paper/2004.02186/) (2020)
- [Online Knowledge Distillation for Efficient Pose Estimation](https://mlsanity.com/paper/2108.02092/) (2021)
- [HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation](https://mlsanity.com/paper/1910.12032/) (2019)
- [4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras](https://mlsanity.com/paper/2002.12625/) (2020)
- [Harvesting Multiple Views for Marker-less 3D Human Pose Annotations](https://mlsanity.com/paper/1704.04793/) (2017)
- [AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild](https://mlsanity.com/paper/2010.13302/) (2020)
- [VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild](https://mlsanity.com/paper/2108.02452/) (2021)
- [Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo](https://mlsanity.com/paper/2104.02273/) (2021)
- [Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images](https://mlsanity.com/paper/2109.05885/) (2021)
- [Context Modeling in 3D Human Pose Estimation: A Unified Perspective](https://mlsanity.com/paper/2103.15507/) (2021)
- [Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimation](https://mlsanity.com/paper/2004.00329/) (2020)
- [Motion Capture from Internet Videos](https://mlsanity.com/paper/2008.07931/) (2020)
- [Voxel-based Network for Shape Completion by Leveraging Edge Generation](https://mlsanity.com/paper/2108.09936/) (2021)
- [Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric Approach](https://mlsanity.com/paper/2003.11163/) (2020)

## Built on by (most cited first, 30 of 39)

- [Human Motion Generation: A Survey](https://mlsanity.com/paper/2307.10894/) (2023)
- [3D Human Mesh Estimation from Virtual Markers](https://mlsanity.com/paper/2303.11726/) (2023)
- [Scene-aware Egocentric 3D Human Pose Estimation](https://mlsanity.com/paper/2212.11684/) (2022)
- [HDFormer: High-order Directed Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2302.01825/) (2023)
- [TEMPO: Efficient Multi-View Pose Estimation, Tracking, and Forecasting](https://mlsanity.com/paper/2309.07910/) (2023)
- [Multiple View Geometry Transformers for 3D Human Pose Estimation](https://mlsanity.com/paper/2311.10983/) (2023)
- [SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens](https://mlsanity.com/paper/2411.19824/) (2024)
- [WorldPose: A World Cup Dataset for Global 3D Human Pose Estimation](https://mlsanity.com/paper/2501.02771/) (2025)
- [Markerless human pose estimation for biomedical applications: a survey](https://mlsanity.com/paper/2308.00519/) (2023)
- [Social Motion Prediction with Cognitive Hierarchies](https://mlsanity.com/paper/2311.04726/) (2023)
- [Markerless Multi-view 3D Human Pose Estimation: a survey](https://mlsanity.com/paper/2407.03817/) (2024)
- [MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation](https://mlsanity.com/paper/2509.00649/) (2025)
- [Reconstructing Close Human Interactions from Multiple Views](https://mlsanity.com/paper/2401.16173/) (2024)
- [AvatarPose: Avatar-guided 3D Pose Estimation of Close Human Interaction from Sparse Multi-view Videos](https://mlsanity.com/paper/2408.02110/) (2024)
- [A Unified Multi-view Multi-person Tracking Framework](https://mlsanity.com/paper/2302.03820/) (2023)
- [CondiMen: Conditional Multi-Person Mesh Recovery](https://mlsanity.com/paper/2412.13058/) (2024)
- [Pre-training a Density-Aware Pose Transformer for Robust LiDAR-based 3D Human Pose Estimation](https://mlsanity.com/paper/2412.13454/) (2024)
- [Kineo: Calibration-Free Metric Motion Capture From Sparse RGB Cameras](https://mlsanity.com/paper/2510.24464/) (2025)
- [VoxelKeypointFusion: Generalizable Multi-View Multi-Person Pose Estimation](https://mlsanity.com/paper/2410.18723/) (2024)
- [Multi-person 3D pose estimation from unlabelled data](https://mlsanity.com/paper/2212.08731/) (2022)
- [Sports Analysis and VR Viewing System Based on Player Tracking and Pose Estimation with Multimodal and Multiview Sensors](https://mlsanity.com/paper/2405.01112/) (2024)
- [Every Angle Is Worth A Second Glance: Mining Kinematic Skeletal Structures from Multi-view Joint Cloud](https://mlsanity.com/paper/2502.02936/) (2025)
- [RapidPoseTriangulation: Multi-view Multi-person Whole-body Human Pose Triangulation in a Millisecond](https://mlsanity.com/paper/2503.21692/) (2025)
- [LiCamPose: Combining Multi-View LiDAR and RGB Cameras for Robust Single-timestamp 3D Human Pose Estimation](https://mlsanity.com/paper/2312.06409/) (2023)
- [SimpleDepthPose: Fast and Reliable Human Pose Estimation with RGBD-Images](https://mlsanity.com/paper/2501.18478/) (2025)
- [P2P-Insole: Human Pose Estimation Using Foot Pressure Distribution and Motion Sensors](https://mlsanity.com/paper/2505.00755/) (2025)
- [Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forward](https://mlsanity.com/paper/2506.03191/) (2025)
- [Shape-aware Inertial Poser: Motion Tracking for Humans with Diverse Shapes Using Sparse Inertial Sensors](https://mlsanity.com/paper/2510.17101/) (2025)
- [COMPOSE: Hypergraph Cover Optimization for Multi-view 3D Human Pose Estimation](https://mlsanity.com/paper/2601.09698/) (2026)
- [Unconstrained Multi-view Human Pose Estimation with Algebraic Priors](https://mlsanity.com/paper/2604.24312/) (2026)

## 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.