# LVI-GS: Tightly-coupled LiDAR-Visual-Inertial SLAM using 3D Gaussian Splatting

arXiv: https://arxiv.org/abs/2411.02703 · HTML: https://mlsanity.com/paper/2411.02703/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2024.

## Built on by (most cited first, 7 of 7)

- [SiLVR: Scalable Lidar-Visual Radiance Field Reconstruction with Uncertainty Quantification](https://mlsanity.com/paper/2502.02657/) (2025)
- [Towards Next-Generation SLAM: A Survey on 3DGS-SLAM Focusing on Performance, Robustness, and Future Directions](https://mlsanity.com/paper/2602.04251/) (2026)
- [ARSGaussian: 3D Gaussian Splatting with LiDAR for Aerial Remote Sensing Novel View Synthesis](https://mlsanity.com/paper/2412.18380/) (2024)
- [EA-3DGS: Efficient and Adaptive 3D Gaussians with Highly Enhanced Quality for outdoor scenes](https://mlsanity.com/paper/2505.10787/) (2025)
- [RoGER-SLAM: A Robust Gaussian Splatting SLAM System for Noisy and Low-light Environment Resilience](https://mlsanity.com/paper/2510.22600/) (2025)
- [GSM-GS: Geometry-Constrained Single and Multi-view Gaussian Splatting for Surface Reconstruction](https://mlsanity.com/paper/2602.12796/) (2026)
- [Transforming Omnidirectional RGB-LiDAR data into 3D Gaussian Splatting](https://mlsanity.com/paper/2603.06061/) (2026)

## Abstract (arXiv)

3D Gaussian Splatting (3DGS) has shown its ability in rapid rendering and high-fidelity mapping. In this paper, we introduce LVI-GS, a tightly-coupled LiDAR-Visual-Inertial mapping framework with 3DGS, which leverages the complementary characteristics of LiDAR and image sensors to capture both geometric structures and visual details of 3D scenes. To this end, the 3D Gaussians are initialized from colourized LiDAR points and optimized using differentiable rendering. In order to achieve high-fidelity mapping, we introduce a pyramid-based training approach to effectively learn multi-level features and incorporate depth loss derived from LiDAR measurements to improve geometric feature perception. Through well-designed strategies for Gaussian-Map expansion, keyframe selection, thread management, and custom CUDA acceleration, our framework achieves real-time photo-realistic mapping. Numerical experiments are performed to evaluate the superior performance of our method compared to state-of-the-art 3D reconstruction systems.