多智能体仅用相机和惯性数据实现高保真三维重建，适合手机端部署。
CGS-SLAM: Collaborative Gaussian Splatting based SLAM for Multi-Agent Reconstruction
- 各智能体用惯性数据辅助跟踪，结合深度估计构建尺度化地图。
- 通过共享关键帧编码，在重叠区域动态优化对齐，提升重建质量。
- 支持无GPS环境下的低通信开销协同重建，适合移动设备应用。
近期的SLAM技术利用3DGS实现了逼真的三维重建与新视角合成，但多数方法依赖RGB-D输入，难以在消费级智能手机上使用，且缺乏在协作框架中集成3DGS的方案。为此，我们提出CGS-SLAM，一种混合去中心化/中心化的多智能体3DGS SLAM系统，仅需RGB和惯性数据。每个智能体利用惯性数据作为运动先验进行局部跟踪，并通过度量单目深度估计器（Depth Pro）重建带尺度的地图。关键帧编码在智能体间共享，实现在空间重叠区域的动态关键帧调整，提升子地图对齐效果。随后，中央服务器使用VGGT作为视图对齐模型进行子地图全局对齐。双向通信机制在映射与全局重建过程中保持低通信开销，适用于无GNSS信号的复杂环境。在多个数据集上的实验表明，该方法在跟踪性能上具有竞争力，渲染质量优于现有最先进方法，且子地图对齐精度高。
原文摘要 · Abstract (English)
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.
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。