# AirPose: Multi-View Fusion Network for Aerial 3D Human Pose and Shape Estimation

arXiv: https://arxiv.org/abs/2201.08093 · HTML: https://mlsanity.com/paper/2201.08093/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 20 Jan 2022.

## Builds on (most cited first, 20 of 20)

- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://mlsanity.com/paper/1909.12828/) (2019)
- [AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles](https://mlsanity.com/paper/1705.05065/) (2017)
- [RMPE: Regional Multi-person Pose Estimation](https://mlsanity.com/paper/1612.00137/) (2016)
- [AGORA: Avatars in Geography Optimized for Regression Analysis](https://mlsanity.com/paper/2104.14643/) (2021)
- [Learnable Triangulation of Human Pose](https://mlsanity.com/paper/1905.05754/) (2019)
- [Towards Accurate Markerless Human Shape and Pose Estimation over Time](https://mlsanity.com/paper/1707.07548/) (2017)
- [Cross View Fusion for 3D Human Pose Estimation](https://mlsanity.com/paper/1909.01203/) (2019)
- [Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation](https://mlsanity.com/paper/2004.02186/) (2020)
- [Harvesting Multiple Views for Marker-less 3D Human Pose Annotations](https://mlsanity.com/paper/1704.04793/) (2017)
- [Shape-Aware Human Pose and Shape Reconstruction Using Multi-View Images](https://mlsanity.com/paper/1908.09464/) (2019)
- [A generalizable approach for multi-view 3D human pose regression](https://mlsanity.com/paper/1804.10462/) (2018)
- [FlyCap: Markerless Motion Capture Using Multiple Autonomous Flying Cameras](https://mlsanity.com/paper/1610.09534/) (2016)
- [MetaFuse: A Pre-trained Fusion Model for Human Pose Estimation](https://mlsanity.com/paper/2003.13239/) (2020)
- [Active Perception based Formation Control for Multiple Aerial Vehicles](https://mlsanity.com/paper/1901.07813/) (2019)
- [Human Motion Capture Using a Drone](https://mlsanity.com/paper/1804.06112/) (2018)
- [Deep Neural Network-based Cooperative Visual Tracking through Multiple Micro Aerial Vehicles](https://mlsanity.com/paper/1802.01346/) (2018)
- [3D Human Pose Estimation from Deep Multi-View 2D Pose](https://mlsanity.com/paper/1902.02841/) (2019)

## Built on by (most cited first, 11 of 11)

- [CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation](https://mlsanity.com/paper/2208.00571/) (2022)
- [Human Pose as Compositional Tokens](https://mlsanity.com/paper/2303.11638/) (2023)
- [Learnable human mesh triangulation for 3D human pose and shape estimation](https://mlsanity.com/paper/2208.11251/) (2022)
- [Proactive Multi-Camera Collaboration For 3D Human Pose Estimation](https://mlsanity.com/paper/2303.03767/) (2023)
- [SmartMocap: Joint Estimation of Human and Camera Motion using Uncalibrated RGB Cameras](https://mlsanity.com/paper/2209.13906/) (2022)
- [Synthetic Data-based Detection of Zebras in Drone Imagery](https://mlsanity.com/paper/2305.00432/) (2023)
- [Half-Physics: Enabling Kinematic 3D Human Model with Physical Interactions](https://mlsanity.com/paper/2507.23778/) (2025)
- [ZebraPose: Zebra Detection and Pose Estimation using only Synthetic Data](https://mlsanity.com/paper/2408.10831/) (2024)
- [Learning from synthetic data generated with GRADE](https://mlsanity.com/paper/2305.04282/) (2023)
- [UAVTwin: Neural Digital Twins for UAVs using Gaussian Splatting](https://mlsanity.com/paper/2504.02158/) (2025)
- [FlyPose: Towards Robust Human Pose Estimation From Aerial Views](https://mlsanity.com/paper/2601.05747/) (2026)

## Abstract (arXiv)

In this letter, we present a novel markerless 3D human motion capture (MoCap) system for unstructured, outdoor environments that uses a team of autonomous unmanned aerial vehicles (UAVs) with on-board RGB cameras and computation. Existing methods are limited by calibrated cameras and off-line processing. Thus, we present the first method (AirPose) to estimate human pose and shape using images captured by multiple extrinsically uncalibrated flying cameras. AirPose itself calibrates the cameras relative to the person instead of relying on any pre-calibration. It uses distributed neural networks running on each UAV that communicate viewpoint-independent information with each other about the person (i.e., their 3D shape and articulated pose). The person's shape and pose are parameterized using the SMPL-X body model, resulting in a compact representation, that minimizes communication between the UAVs. The network is trained using synthetic images of realistic virtual environments, and fine-tuned on a small set of real images. We also introduce an optimization-based post-processing method (AirPose+) for offline applications that require higher MoCap quality. We make our method's code and data available for research at https://github.com/robot-perception-group/AirPose. A video describing the approach and results is available at https://youtu.be/xLYe1TNHsfs.