用无人机视频实时重建高保真3D场景，延迟更低、效果接近离线方法。
Large-scale Photorealistic Outdoor 3D Scene Reconstruction from UAV Imagery Using Gaussian Splatting Techniques
- 融合无人机视频流与传感器数据，实时估计相机位姿并优化3D高斯点云。
- 相比NeRF方法，渲染速度更快，端到端延迟显著降低，视觉质量仅差4-7%。
- 适合需要低延迟沉浸式体验的空中感知、AR/VR应用，支持持续更新。
本研究提出一种端到端管道，可将无人机采集的视频流转化为高保真3D重建，具备极低延迟。无人机广泛应用于空域实时感知，而近期3D高斯泼溅（3DGS）在实时神经渲染方面展现出巨大潜力。然而，其在基于无人机的端到端重建与可视化系统中的集成仍不充分。本文目标是设计一个高效架构，结合RTMP流式视频获取、同步传感器融合、相机位姿估计及3DGS优化，实现连续模型更新与低延迟部署，支持沉浸式增强现实（AR）与虚拟现实（VR）应用。实验表明，该方法在视觉保真度上表现优异，渲染性能显著优于基于NeRF的方法，且端到端延迟大幅降低；重建质量仅比高保真离线参考结果低4-7%，证实了系统在空中平台实时可扩展感知中的适用性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。