Neural LiDAR Bundle Adjustment
For researchers working on LiDAR-based 3D mapping and SLAM, this work addresses the specific bottleneck of volume sampling in LiDAR NeRFs, offering a tailored bundle adjustment method.
The paper identifies volume sampling density as a key factor in LiDAR NeRF and proposes Neural LiDAR Bundle Adjustment (NeLD-BA) for joint optimization of LiDAR map and poses, achieving state-of-the-art performance in multi-view point cloud registration and 3D mapping on Newer College and FusionPortable datasets.
Recent research has achieved remarkable novel view rendering and scene reconstruction results with Neural Radiance Field (NeRF), including extensions to the LiDAR modality. Few studies have, however, explored the key design differences between RGB NeRFs and LiDAR NeRFs, particularly considering their underlying working principles. In this work, we provide both theoretical and empirical evidence suggesting that the density of volume sampling plays a significant role in LiDAR NeRF. Based on this finding, we propose a novel Neural LiDAR Bundle Adjustment (NeLD-BA) algorithm, which is tailored using efficient volume sampling of LiDAR rays for joint optimization of LiDAR map and poses. Extensive experiments are performed using the Newer College and FusionPortable datasets to demonstrate the proposed NeLD-BA's state-of-the-art performance in multi-view point cloud registration and 3D mapping. We will open-source our code for the community.