# A generalizable approach for multi-view 3D human pose regression

arXiv: https://arxiv.org/abs/1804.10462 · HTML: https://mlsanity.com/paper/1804.10462/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2018.

## Built on by (most cited first, 26 of 26)

- [Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2103.14304/) (2021)
- [Direct Multi-view Multi-person 3D Pose Estimation](https://mlsanity.com/paper/2111.04076/) (2021)
- [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)
- [Reconstructing People, Places, and Cameras](https://mlsanity.com/paper/2412.17806/) (2024)
- [Generalizable Human Pose Triangulation](https://mlsanity.com/paper/2110.00280/) (2021)
- [TEMPO: Efficient Multi-View Pose Estimation, Tracking, and Forecasting](https://mlsanity.com/paper/2309.07910/) (2023)
- [SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation](https://mlsanity.com/paper/2404.02041/) (2024)
- [Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2110.05092/) (2021)
- [Learnable human mesh triangulation for 3D human pose and shape estimation](https://mlsanity.com/paper/2208.11251/) (2022)
- [Graph Neural Networks for Cross-Camera Data Association](https://mlsanity.com/paper/2201.06311/) (2022)
- [FLEX: Extrinsic Parameters-free Multi-view 3D Human Motion Reconstruction](https://mlsanity.com/paper/2105.01937/) (2021)
- [AirPose: Multi-View Fusion Network for Aerial 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2201.08093/) (2022)
- [Markerless Multi-view 3D Human Pose Estimation: a survey](https://mlsanity.com/paper/2407.03817/) (2024)
- [3D Human Pose Estimation in Multi-View Operating Room Videos Using Differentiable Camera Projections](https://mlsanity.com/paper/2210.11826/) (2022)
- [View Consistency Aware Holistic Triangulation for 3D Human Pose Estimation](https://mlsanity.com/paper/2302.11301/) (2023)
- [GTA-Net: An IoT-Integrated 3D Human Pose Estimation System for Real-Time Adolescent Sports Posture Correction](https://mlsanity.com/paper/2411.06725/) (2024)
- [Open surgery tool classification and hand utilization using a multi-camera system](https://mlsanity.com/paper/2111.06098/) (2021)
- [VoxelKeypointFusion: Generalizable Multi-View Multi-Person Pose Estimation](https://mlsanity.com/paper/2410.18723/) (2024)
- [High Fidelity 3D Reconstructions with Limited Physical Views](https://mlsanity.com/paper/2110.11599/) (2021)
- [RUMPL: Ray-Based Transformers for Universal Multi-View 2D to 3D Human Pose Lifting](https://mlsanity.com/paper/2512.15488/) (2025)
- [MBW: Multi-view Bootstrapping in the Wild](https://mlsanity.com/paper/2210.01721/) (2022)
- [SimpleDepthPose: Fast and Reliable Human Pose Estimation with RGBD-Images](https://mlsanity.com/paper/2501.18478/) (2025)
- [Unconstrained Multi-view Human Pose Estimation with Algebraic Priors](https://mlsanity.com/paper/2604.24312/) (2026)
- [DeProPose: Deficiency-Proof 3D Human Pose Estimation via Adaptive Multi-View Fusion](https://mlsanity.com/paper/2502.16419/) (2025)

## Abstract (arXiv)

Despite the significant improvement in the performance of monocular pose estimation approaches and their ability to generalize to unseen environments, multi-view (MV) approaches are often lagging behind in terms of accuracy and are specific to certain datasets. This is mainly due to the fact that (1) contrary to real world single-view (SV) datasets, MV datasets are often captured in controlled environments to collect precise 3D annotations, which do not cover all real world challenges, and (2) the model parameters are learned for specific camera setups. To alleviate these problems, we propose a two-stage approach to detect and estimate 3D human poses, which separates SV pose detection from MV 3D pose estimation. This separation enables us to utilize each dataset for the right task, i.e. SV datasets for constructing robust pose detection models and MV datasets for constructing precise MV 3D regression models. In addition, our 3D regression approach only requires 3D pose data and its projections to the views for building the model, hence removing the need for collecting annotated data from the test setup. Our approach can therefore be easily generalized to a new environment by simply projecting 3D poses into 2D during training according to the camera setup used at test time. As 2D poses are collected at test time using a SV pose detector, which might generate inaccurate detections, we model its characteristics and incorporate this information during training. We demonstrate that incorporating the detector's characteristics is important to build a robust 3D regression model and that the resulting regression model generalizes well to new MV environments. Our evaluation results show that our approach achieves competitive results on the Human3.6M dataset and significantly improves results on a MV clinical dataset that is the first MV dataset generated from live surgery recordings.