# Consensus-based Optimization for 3D Human Pose Estimation in Camera Coordinates

arXiv: https://arxiv.org/abs/1911.09245 · HTML: https://mlsanity.com/paper/1911.09245/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2019.

## Built on by (most cited first, 9 of 9)

- [Scene-Aware 3D Multi-Human Motion Capture from a Single Camera](https://mlsanity.com/paper/2301.05175/) (2023)
- [Monocular 3D Human Pose Estimation for Sports Broadcasts using Partial Sports Field Registration](https://mlsanity.com/paper/2304.04437/) (2023)
- [Deep learning for 3D human pose estimation and mesh recovery: A survey](https://mlsanity.com/paper/2402.18844/) (2024)
- [GTA-Net: An IoT-Integrated 3D Human Pose Estimation System for Real-Time Adolescent Sports Posture Correction](https://mlsanity.com/paper/2411.06725/) (2024)
- [STGFormer: Spatio-Temporal GraphFormer for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2407.10099/) (2024)
- [Markerless 3D human pose tracking through multiple cameras and AI: Enabling high accuracy, robustness, and real-time performance](https://mlsanity.com/paper/2303.18119/) (2023)
- [RCR: Robust Crowd Reconstruction with Upright Space from a Single Large-scene Image](https://mlsanity.com/paper/2411.06232/) (2024)
- [Unconstrained Multi-view Human Pose Estimation with Algebraic Priors](https://mlsanity.com/paper/2604.24312/) (2026)
- [Szloca: towards a framework for full 3D tracking through a single camera in context of interactive arts](https://mlsanity.com/paper/2206.12958/) (2022)

## Abstract (arXiv)

3D human pose estimation is frequently seen as the task of estimating 3D poses relative to the root body joint. Alternatively, we propose a 3D human pose estimation method in camera coordinates, which allows effective combination of 2D annotated data and 3D poses and a straightforward multi-view generalization. To that end, we cast the problem as a view frustum space pose estimation, where absolute depth prediction and joint relative depth estimations are disentangled. Final 3D predictions are obtained in camera coordinates by the inverse camera projection. Based on this, we also present a consensus-based optimization algorithm for multi-view predictions from uncalibrated images, which requires a single monocular training procedure. Although our method is indirectly tied to the training camera intrinsics, it still converges for cameras with different intrinsic parameters, resulting in coherent estimations up to a scale factor. Our method improves the state of the art on well known 3D human pose datasets, reducing the prediction error by 32% in the most common benchmark. We also reported our results in absolute pose position error, achieving 80~mm for monocular estimations and 51~mm for multi-view, on average.