Large-scale Photorealistic Outdoor 3D Scene Reconstruction from UAV Imagery Using Gaussian Splatting Techniques

TL;DR

This paper introduces a real-time UAV-based 3D scene reconstruction system using Gaussian Splatting, achieving high visual fidelity and low latency suitable for AR/VR applications, outperforming traditional NeRF methods.

Contribution

The paper presents an integrated end-to-end pipeline combining live UAV video, sensor fusion, camera pose estimation, and 3D Gaussian Splatting for real-time outdoor 3D reconstruction.

Findings

Achieves 4-7% reconstruction quality loss compared to offline references.

Significantly improves rendering performance and reduces latency over NeRF-based methods.

Supports immersive AR/VR visualization with scalable, real-time 3D models.

Abstract

In this study, we present an end-to-end pipeline capable of converting drone-captured video streams into high-fidelity 3D reconstructions with minimal latency. Unmanned aerial vehicles (UAVs) are extensively used in aerial real-time perception applications. Moreover, recent advances in 3D Gaussian Splatting (3DGS) have demonstrated significant potential for real-time neural rendering. However, their integration into end-to-end UAV-based reconstruction and visualization systems remains underexplored. Our goal is to propose an efficient architecture that combines live video acquisition via RTMP streaming, synchronized sensor fusion, camera pose estimation, and 3DGS optimization, achieving continuous model updates and low-latency deployment within interactive visualization environments that supports immersive augmented and virtual reality (AR/VR) applications. Experimental results demonstrate that the proposed method achieves competitive visual fidelity, while delivering significantly higher rendering performance and substantially reduced end-to-end latency, compared to NeRF-based approaches. Reconstruction quality remains within 4-7\% of high-fidelity offline references, confirming the suitability of the proposed system for real-time, scalable augmented perception from aerial platforms.