analiza aiqbench
MCGS-SLAM represents a significant methodological shift by leveraging 3D Gaussian Splatting to create dense, photorealistic maps from multi-camera RGB inputs without relying on inertial sensors or sparse point clouds. This approach directly addresses the geometric coverage limitations of monocular systems, offering improved robustness for autonomous driving and robotics through enhanced side-view reconstruction. The framework's ability to maintain real-time performance while optimizing a unified Gaussian map underscores the growing viability of neural rendering techniques for practical SLAM applications.
MCGS-SLAM: A Multi-Camera SLAM Framework Using Gaussian Splatting for High-Fidelity Mapping
arXiv:2509.14191v4 Announce Type: replace Abstract: Recent progress in dense SLAM has primarily targeted monocular setups, often at the expense of robustness and geometric coverage. We present MCGS-SLAM, the first purely RGB-based multi-camera SLAM system built on 3D Gaussian Splatting (3DGS). Unlike prior methods relying on sparse maps or inertial data, MCGS-SLAM fuses dense RGB inputs from multiple viewpoints into a unified, continuously optimized Gaussian map. A multi-camera bundle adjustment (MCBA) jointly refines poses and depths via dense photometric and geometric residuals, while a scale consistency module enforces metric alignment across views using low-rank priors. The system supports RGB input and maintains real-time performance at large scale. Experiments on synthetic and real-world datasets show that MCGS-SLAM consistently yields accurate trajectories and photorealistic reconstructions, usually outperforming monocular baselines. Notably, the wide field of view from multi-camera input enables reconstruction of side-view regions that monocular setups miss, critical for safe autonomous operation. These results highlight the promise of multi-camera Gaussian Splatting SLAM for high-fidelity mapping in robotics and autonomous driving.
Abstract:Recent progress in dense SLAM has primarily targeted monocular setups, often at the expense of robustness and geometric coverage. We present MCGS-SLAM, the first purely RGB-based multi-camera SLAM system built on 3D Gaussian Splatting (3DGS). Unlike prior methods relying on sparse maps or inertial data, MCGS-SLAM fuses dense RGB inputs from multiple viewpoints into a unified, continuously optimized Gaussian map. A multi-camera bundle adjustment (MCBA) jointly refines poses and depths via dense photometric and geometric residuals, while a scale consistency module enforces metric alignment across views using low-rank priors. The system supports RGB input and maintains real-time performance at large scale. Experiments on synthetic and real-world datasets show that MCGS-SLAM consistently yields accurate trajectories and photorealistic reconstructions, usually outperforming monocular baselines. Notably, the wide field of view from multi-camera input enables reconstruction of side-view regions that monocular setups miss, critical for safe autonomous operation. These results highlight the promise of multi-camera Gaussian Splatting SLAM for high-fidelity mapping in robotics and autonomous driving.
Accepted to IEEE International Conference on Robotics and Automation (ICRA) 2026. Code: this https URL
Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2509.14191 [cs.RO]
(or arXiv:2509.14191v4 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2509.14191 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 · 274 cuvinte
Subiecte conexe
MAGS-SLAM: Monocular Multi-Agent Gaussian Splatting SLAM for Geometrically and Photometrically Consistent Reconstruction
arXiv · 28 iul. 2026
Breaking Time: A Fully Gaussian Framework for Distributed and Continuous-Time SLAM
arXiv · 5 iun. 2026
RoSe-SLAM: Robust Semantic-Aware Gaussian Splatting SLAM from Dynamic Monocular Videos
arXiv · 1 sept. 2026
[AINews] not much happened today
Latent Space · 18 sept. 2026