融合激光雷达与视觉惯性数据，实现实时高保真三维地图构建
LVI-GS: Tightly-coupled LiDAR-Visual-Inertial SLAM using 3D Gaussian Splatting
- 用彩色激光点初始化3D高斯分布，通过可微渲染优化
- 引入金字塔训练和深度损失，提升几何感知精度
- 支持实时运行，适合自动驾驶与机器人场景
3D Gaussian Splatting（3DGS）在快速渲染和高保真建图方面展现出潜力。本文提出LVI-GS，一种基于3DGS的紧耦合激光雷达-视觉-惯性定位与建图框架，利用激光雷达与图像传感器的互补特性，同时捕捉三维场景的几何结构与视觉细节。3D高斯分布从彩色激光点初始化，并通过可微渲染进行优化。为实现高保真建图，引入基于金字塔的训练策略以有效学习多层级特征，并结合来自激光雷达测量的深度损失以增强几何特征感知。通过精心设计的高斯地图扩展、关键帧选择、线程管理及定制CUDA加速策略，本框架实现了实时照片级真实感建图。数值实验表明，该方法在性能上优于当前最先进的三维重建系统。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。