As Neural Radiance Field (NeRF) implementations become faster, more efficient and accurate, their applicability to real world mapping tasks becomes more accessible. Traditionally, 3D mapping, or scene reconstruction, has relied on expensive LiDAR sensing. Photogrammetry can perform image-based 3D reconstruction but is computationally expensive and requires extremely dense image representation to recover complex geometry and photorealism. NeRFs perform 3D scene reconstruction by training a neural network on sparse image and pose data, achieving superior results to photogrammetry with less input data. This paper presents an evaluation of two NeRF scene reconstructions for the purpose of estimating the diameter of a vertical PVC cylinder. One of these are trained on commodity iPhone data and the other is trained on robot-sourced imagery and poses. This neural-geometry is compared to state-of-the-art lidar-inertial SLAM in terms of scene noise and metric-accuracy.

翻译：随着神经辐射场（NeRF）实现方法在速度、效率和精度上的不断提升，其在实际地图构建任务中的应用可行性显著增强。传统的三维建图（或称场景重建）长期依赖昂贵的激光雷达传感技术。摄影测量虽能实现基于图像的三维重建，但计算成本高昂，且需要极高密度的图像覆盖才能还原复杂几何结构与真实感。NeRF通过基于稀疏图像与位姿数据训练神经网络完成三维场景重建，在输入数据更少的情况下取得了优于摄影测量的结果。本文针对竖直PVC圆柱体的直径估计任务，评估了两种NeRF场景重建方法：其一基于消费级iPhone采集的数据训练，其二基于机器人采集的图像与位姿数据训练。研究从场景噪声与度量精度两个维度，将此类神经几何重建方法与最先进的激光雷达-惯性SLAM技术进行了对比分析。