We present a neural-field-based large-scale reconstruction system that fuses lidar and vision data to generate high-quality reconstructions that are geometrically accurate and capture photo-realistic textures. This system adapts the state-of-the-art neural radiance field (NeRF) representation to also incorporate lidar data which adds strong geometric constraints on the depth and surface normals. We exploit the trajectory from a real-time lidar SLAM system to bootstrap a Structure-from-Motion (SfM) procedure to both significantly reduce the computation time and to provide metric scale which is crucial for lidar depth loss. We use submapping to scale the system to large-scale environments captured over long trajectories. We demonstrate the reconstruction system with data from a multi-camera, lidar sensor suite onboard a legged robot, hand-held while scanning building scenes for 600 metres, and onboard an aerial robot surveying a multi-storey mock disaster site-building. Website: https://ori-drs.github.io/projects/silvr/

翻译：我们提出了一种基于神经场的大规模重建系统，融合激光雷达与视觉数据，生成兼具几何精度与照片级真实感纹理的高质量重建。该系统将前沿的神经辐射场（NeRF）表征扩展至激光雷达数据，通过深度与表面法向量引入强几何约束。我们利用实时激光雷达SLAM系统的轨迹来引导运动恢复结构（SfM）流程，既显著降低了计算时间，又提供了对激光雷达深度损失至关重要的度量尺度。通过子图映射技术，该系统可扩展至覆盖长轨迹的大尺度环境。我们使用搭载于腿足机器人、手持扫描600米建筑场景的传感器套件（多摄像头与激光雷达组合），以及空中机器人对多层模拟灾害遗址进行勘察的实验数据，验证了该重建系统的性能。网站：https://ori-drs.github.io/projects/silvr/