# RMGS-SLAM: Real-time Multi-sensor Gaussian Splatting SLAM

arXiv: https://arxiv.org/abs/2604.12942 · HTML: https://mlsanity.com/paper/2604.12942/

## Key facts

- Cited by 1 papers in the map (data through 19 Oct 2026).
- Placed in SLAM and driving scene reconstruction, one of 15 directions in 3D reconstruction and neural rendering.
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Placed in

- 3D reconstruction and neural rendering / [SLAM and driving scene reconstruction](https://mlsanity.com/recon3d/slam-and-driving-scene-reconstruction/)

## Builds on (most cited first, 21 of 21)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [Gaussian Splatting SLAM](https://mlsanity.com/paper/2312.06741/) (2023)
- [SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM](https://mlsanity.com/paper/2312.02126/) (2023)
- [Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age](https://mlsanity.com/paper/1606.05830/) (2016)
- [DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes](https://mlsanity.com/paper/2312.07920/) (2023)
- [GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting](https://mlsanity.com/paper/2311.11700/) (2023)
- [DepthSplat: Connecting Gaussian Splatting and Depth](https://mlsanity.com/paper/2410.13862/) (2024)
- [No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images](https://mlsanity.com/paper/2410.24207/) (2024)
- [FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry](https://mlsanity.com/paper/2408.14035/) (2024)
- [LIV-GaussMap: LiDAR-Inertial-Visual Fusion for Real-time 3D Radiance Field Map Rendering](https://mlsanity.com/paper/2401.14857/) (2024)
- [BALM: Bundle Adjustment for Lidar Mapping](https://mlsanity.com/paper/2010.08215/) (2020)
- [Gaussian-LIC: Real-Time Photo-Realistic SLAM with Gaussian Splatting and LiDAR-Inertial-Camera Fusion](https://mlsanity.com/paper/2404.06926/) (2024)
- [Efficient and Probabilistic Adaptive Voxel Mapping for Accurate Online LiDAR Odometry](https://mlsanity.com/paper/2109.07082/) (2021)
- [LiV-GS: LiDAR-Vision Integration for 3D Gaussian Splatting SLAM in Outdoor Environments](https://mlsanity.com/paper/2411.12185/) (2024)
- [VPGS-SLAM: Voxel-based Progressive 3D Gaussian SLAM in Large-Scale Scenes](https://mlsanity.com/paper/2505.18992/) (2025)
- [GS-LIVM: Real-Time Photo-Realistic LiDAR-Inertial-Visual Mapping with Gaussian Splatting](https://mlsanity.com/paper/2410.17084/) (2024)
- [GS-LIVO: Real-Time LiDAR, Inertial, and Visual Multi-sensor Fused Odometry with Gaussian Mapping](https://mlsanity.com/paper/2501.08672/) (2025)
- [LVI-GS: Tightly-coupled LiDAR-Visual-Inertial SLAM using 3D Gaussian Splatting](https://mlsanity.com/paper/2411.02703/) (2024)
- [Gaussian-LIC2: LiDAR-Inertial-Camera Gaussian Splatting SLAM](https://mlsanity.com/paper/2507.04004/) (2025)

## Built on by (most cited first, 1 of 1)

- [MIRAGE: Metric Inference and Reliability-Aware Gaussian Estimation from Feed-Forward Vision](https://mlsanity.com/paper/2610.12568/) (2026)

## Abstract (arXiv)

Achieving real-time Simultaneous Localization and Mapping (SLAM) based on 3D Gaussian splatting (3DGS) in large-scale real-world environments remains challenging, as existing methods still struggle to jointly achieve low-latency pose estimation, continuous 3D Gaussian reconstruction, and long-term global consistency. In this paper, we present a tightly coupled LiDAR-Inertial-Visual 3DGS-based SLAM framework for real-time pose estimation and photorealistic mapping in large-scale real-world scenes. The system executes state estimation and 3D Gaussian primitive initialization in parallel with global Gaussian optimization, enabling continuous dense mapping. To improve Gaussian initialization quality and accelerate optimization convergence, we introduce a cascaded strategy that combines feed-forward predictions with geometric priors derived from voxel-based principal component analysis. To enhance global consistency, we perform loop closure directly on the optimized global Gaussian map by estimating loop constraints through Gaussian-based Generalized Iterative Closest Point registration, followed by pose-graph optimization. We also collect challenging large-scale looped outdoor sequences with hardware-synchronized LiDAR-camera-IMU and ground-truth trajectories for realistic evaluation. Extensive experiments on both public datasets and our dataset demonstrate that the proposed method achieves a state of the art among real-time efficiency, localization accuracy, and rendering quality across diverse real-world scenes.