CGS-SLAM：基于协作高斯溅射（Gaussian Splatting）的多智能体重建SLAM算法

中文摘要 AI 辅助

近期SLAM领域的进展已利用3DGS实现了照片级真实感重建和新视角合成。然而，大多数方法依赖RGB-D输入，而消费级智能手机无法获取该输入，且很少有方法将3DGS集成到协作框架中。因此，我们提出CGS-SLAM，这是一种混合去中心化/集中式系统，仅使用RGB和惯性数据即可实现多智能体3DGS SLAM。每个智能体以惯性数据作为运动先验执行局部跟踪，并使用度量单目深度估计器（Depth Pro）重建缩放后的地图。关键帧编码在智能体之间共享，支持在与其他智能体空间重叠的区域进行动态关键帧设置，增强子图对齐。之后，中央服务器使用VGGT作为视角对齐模型对齐子图。这种双向通信在GNSS拒止环境的建图和全局重建过程中保持通信成本较低。在多个数据集上的实验表明，该算法具有竞争力的跟踪性能，相比现有方法提升了渲染质量，且子图对齐准确。

英文摘要

Recent advances in SLAM have leveraged 3DGS for photorealistic reconstruction and novel view synthesis. However, most methods rely on RGB-D input, which is unavailable on consumer-grade smartphones, and few integrate 3DGS within a collaborative framework. Therefore, we present CGS-SLAM, a hybrid decentralized/centralized system enabling multi-agent 3DGS SLAM using only RGB and inertial data. Each agent performs local tracking with inertial data as a motion prior and reconstructs a scaled map using a metric monocular depth estimator (Depth Pro). Keyframe encodings are shared among agents, enabling dynamic keyframing in regions of spatial overlaps with other agents, enhancing submap alignment. Afterwards, a central server aligns submaps using VGGT as a view alignment model. This bidirectional communication keeps communication cost low during mapping and global reconstruction in difficult GNSS-denied environments. Experiments on multiple datasets demonstrate competitive tracking performance, improved rendering quality over state-of-the-art methods, and accurate submap alignment.

发表机构

• Université Sorbonne Paris Nord（巴黎北大学）
• SAS IMPACT（SAS IMPACT公司）
• Université d’Orléans（奥尔良大学）
• INSA CVL（中央卢瓦尔河谷国立应用科学学院）

机构由 AI 辅助整理，请以论文原文为准。