We introduce an integrated precise LiDAR, Inertial, and Visual (LIV) multi-modal sensor fused mapping system that builds on the differentiable surface splatting to improve the mapping fidelity, quality, and structural accuracy. Notably, this is also a novel form of tightly coupled map for LiDAR-visual-inertial sensor fusion. This system leverages the complementary characteristics of LiDAR and visual data to capture the geometric structures of large-scale 3D scenes and restore their visual surface information with high fidelity. The initial poses for surface Gaussian scenes are obtained using a LiDAR-inertial system with size-adaptive voxels. Then, we optimized and refined the Gaussians by visual-derived photometric gradients to optimize the quality and density of LiDAR measurements. Our method is compatible with various types of LiDAR, including solid-state and mechanical LiDAR, supporting both repetitive and non-repetitive scanning modes. bolstering structure construction through LiDAR and facilitating real-time generation of photorealistic renderings across diverse LIV datasets. It showcases notable resilience and versatility in generating real-time photorealistic scenes potentially for digital twins and virtual reality while also holding potential applicability in real-time SLAM and robotics domains. We release our software and hardware and self-collected datasets on Github\footnote[3]{https://github.com/sheng00125/LIV-GaussMap} to benefit the community.

翻译：我们提出了一种集成精确激光、惯性及视觉多模态传感器融合建图系统，该系统基于可微分表面溅射技术，旨在提升建图保真度、质量与结构精度。值得注意的是，这也是激光-视觉-惯性传感器融合中一种新型紧耦合地图形式。该系统利用激光与视觉数据的互补特性，捕捉大规模三维场景的几何结构，并以高保真度恢复其视觉表面信息。通过采用尺寸自适应体素的激光-惯性系统获取表面高斯场景的初始位姿，进而利用视觉衍生的光度梯度优化与精化高斯参数，以提升激光测量质量与密度。我们的方法兼容包括固态与机械式激光雷达在内的多种型号，支持重复与非重复扫描模式。借助激光强化结构构建，并在多样化激光-惯性-视觉数据集上实现照片级渲染的实时生成。该方法在生成潜在用于数字孪生与虚拟现实的实时照片级场景时展现出显著的鲁棒性与通用性，同时具备在实时SLAM及机器人领域的潜在应用价值。我们已在Github上开源相关软硬件及自采集数据集（https://github.com/sheng00125/LIV-GaussMap），以回馈社区。