跳到正文
arXiv · virtual production· Zhihao Cao·精选AI 评分52

MAGS-SLAM:面向几何与光度一致重建的单目多智能体高斯泼溅 SLAM

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

AI 导读

作者提出 MAGS-SLAM,这是一个仅用 RGB 图像的多智能体 3DGS SLAM 框架,用于协同场景重建。每个智能体独立构建局部单目高斯子图,并传输紧凑的子图摘要而非原始观测;框架结合几何与外观感知的回环验证以及占用感知的高斯融合,以应对单目尺度歧义。

推荐理由

论文提出仅用 RGB 相机的多智能体 3DGS SLAM 框架,并给出与 RGB-D 方法对比的实验结果,可供关注大场景重建的虚拟制作团队参考。

正文 · 原文

View PDF HTML (experimental)

Abstract: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. 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 both synthetic and real-world datasets demonstrate that MAGS-SLAM, using RGB images alone, achieves tracking accuracy, rendering quality, and geometric quality that are competitive with or superior to those of state-of-the-art RGB-D collaborative Gaussian SLAM methods.
Comments: Accepted to IEEE Transactions on Automation Science and Engineering (T-ASE) 2026, project website: this https URL
Subjects: Robotics (cs.RO)
Cite as: arXiv:2605.10760 [cs.RO]
  (or arXiv:2605.10760v3 [cs.RO] for this version)
  https://doi.org/10.48550/arXiv.2605.10760

arXiv-issued DOI via DataCite

Submission history

From: Zhihao Cao [view email]
[v1] Mon, 11 May 2026 15:57:13 UTC (47,763 KB)
[v2] Mon, 27 Jul 2026 16:55:44 UTC (2,648 KB)
[v3] Mon, 19 Oct 2026 01:37:01 UTC (2,649 KB)

来源:arXiv · virtual production · arxiv.org