analiza aiqbench
This research introduces MAGS-SLAM, a novel framework enabling collaborative 3D reconstruction using only RGB cameras by eliminating the need for expensive depth sensors. By transmitting compact submap summaries and integrating geometry-aware loop verification, it achieves high-fidelity mapping suitable for low-cost robotic platforms and virtual production environments. The work establishes a new benchmark with larger robot teams to evaluate cooperative Gaussian Splatting systems in real-world scenarios.
MAGS-SLAM: Monocular Multi-Agent Gaussian Splatting SLAM for Geometrically and Photometrically Consistent Reconstruction
arXiv:2605.10760v2 Announce Type: replace 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 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.
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 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.
Robotics (cs.RO)
arXiv:2605.10760 [cs.RO]
(or arXiv:2605.10760v2 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2605.10760 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 282 cuvinte
Subiecte conexe
CGS-SLAM: Collaborative Gaussian Splatting based SLAM for Multi-Agent Reconstruction
arXiv · 28 aug. 2026
MCGS-SLAM: A Multi-Camera SLAM Framework Using Gaussian Splatting for High-Fidelity Mapping
arXiv · 9 sept. 2026
RoSe-SLAM: Robust Semantic-Aware Gaussian Splatting SLAM from Dynamic Monocular Videos
arXiv · 1 sept. 2026
GLAM-SLAM: Real-time Gaussian Large-scale Mapping via Flow Densification and Spatial Decomposition
arXiv · 24 iul. 2026