Abstract
We present a real-time LiDAR-Inertial-Camera SLAM system with 3D Gaussian Splatting as the mapping backend. Leveraging robust pose estimates from our LiDAR-Inertial-Camera odometry, Coco-LIC, an incremental photo-realistic mapping system is proposed in this paper. We initialize 3D Gaussians from colorized LiDAR points and optimize them using differentiable rendering powered by 3D Gaussian Splatting. Meticulously designed strategies are employed to incrementally expand the Gaussian map and adaptively control its density, ensuring high-quality mapping with real-time capability. Experiments conducted in diverse scenarios demonstrate the superior performance of our method compared to existing radiance-field-based SLAM systems.
Abstract (translated)
我们提出了一个基于真实时间LiDAR-Inertial-Camera SLAM系统,其3D高斯平铺作为映射后端。利用来自LiDAR-Inertial-Camera odometry的稳健姿态估计,我们提出了一个逐步照片现实主义的映射系统——Coco-LIC。我们使用由彩色LiDAR点初始化的3D高斯,并使用基于3D高斯平铺的差分渲染进行优化。我们采用精心设计的策略来逐步扩展高斯图,并适当地控制其密度,以确保具有实时能力的高质量映射。在不同的场景中进行实验,证明了我们的方法与现有基于辐射场SLAM系统的优越性能相比具有更高的性能。
URL
https://arxiv.org/abs/2404.06926