arXiv 2605.107602026-07-28cs.RO

MAGS-SLAM：单目多智能体高斯点云SLAM用于几何和光度一致的重建

MAGS-SLAM: Monocular Multi-Agent Gaussian Splatting SLAM for Geometrically and Photometrically Consistent Reconstruction

ETH Zurich（苏黎世联邦理工学院）；Harbin Engineering University（哈尔滨工程大学）；University of Liverpool（利物浦大学）；University of Macau（澳门大学）；University of Ottawa（多伦多大学）；Wuhan University（武汉大学）；Imperial College London（伦敦帝国学院）

Zhihao Cao, Qi Shao, Shuhao Zhai, Jing Zhang, Anh Nguyen, Hesheng Wang, Baoru Huang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

MAGS-SLAM通过单目视觉实现多智能体高斯点云SLAM，无需RGB-D传感器即可完成几何和光度一致的场景重建，实验表明其跟踪精度和渲染质量可与现有RGB-D方法媲美。

摘要：

协作式真实感3D重建从多个智能体能够快速进行大规模场景捕获，用于虚拟生产和协作多机器人探索。尽管最近的3D高斯点云（3DGS）SLAM算法可以生成高保真的实时映射，但大多数现有的多智能体高斯SLAM方法仍依赖RGB-D传感器获取度量深度并简化跨智能体对齐，这限制了在轻量、低成本或电力受限的机器人平台上的部署。为了解决这一挑战，我们提出了MAGS-SLAM，这是首个仅使用RGB图像的多智能体3DGS SLAM框架，用于协作场景重建。每个智能体独立构建局部单目高斯子地图，并传输紧凑的子地图摘要，而不是原始观测或密集地图。为了在存在单目尺度模糊的情况下实现稳健的协作，我们的框架集成了紧凑的子地图通信、几何和外观感知的环路验证以及占用感知的高斯融合，使能够实现一致的全局重建而无需主动深度传感器。我们进一步引入了ReplicaMultiagent Plus基准测试用于评估协作高斯SLAM。在合成和真实世界数据集上的密集实验表明，MAGS-SLAM在仅依赖RGB图像的情况下实现了竞争性的跟踪精度和可比或更优的渲染质量，与现有最先进的RGB-D协作高斯SLAM方法相当。

英文摘要：

Collaborative photorealistic 3D reconstruction from multiple agents enables rapid large-scale scene capture for virtual production and cooperative multi-robot exploration. While recent 3D Gaussian Splatting (3DGS) SLAM algorithms can generate high-fidelity real-time mapping, most of the existing multi-agent Gaussian SLAM methods still rely on RGB-D sensors to obtain metric depth and simplify cross-agent alignment, limiting their deployment on low-cost or power-constrained robotic platforms, especially given the wider availability of RGB cameras. To address this challenge, we propose MAGS-SLAM, the first RGB-only multi-agent 3DGS SLAM framework for collaborative scene reconstruction. Each agent independently builds local monocular Gaussian submaps and transmits compact submap summaries rather than raw observations or dense maps. To facilitate robust collaboration in the presence of monocular scale ambiguity, our framework integrates compact submap communication, geometry- and appearance-aware loop verification, and occupancy-aware Gaussian fusion, enabling coherent global reconstruction without active depth sensors. We further introduce ReplicaMultiagent Plus, a benchmark containing larger robot teams for evaluating collaborative Gaussian SLAM. Extensive experiments on synthetic and real-world datasets show that MAGS-SLAM achieves tracking accuracy and rendering quality competitive with or superior to those of state-of-the-art RGB-D collaborative Gaussian SLAM methods using RGB images alone.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。