Efficient Implicit Neural Reconstruction Using LiDAR

TL;DR

This paper introduces a novel LiDAR-based implicit scene reconstruction method that efficiently produces detailed 3D models without requiring dense data or global registration, outperforming previous approaches in various settings.

Contribution

It presents the first LiDAR-only implicit scene reconstruction technique that refines poses end-to-end and avoids information loss with a new 3D supervision loss.

Findings

Effective on synthetic and real-world datasets

Produces comparable results with dense-input methods

Reconstructs scenes efficiently within minutes

Abstract

Modeling scene geometry using implicit neural representation has revealed its advantages in accuracy, flexibility, and low memory usage. Previous approaches have demonstrated impressive results using color or depth images but still have difficulty handling poor light conditions and large-scale scenes. Methods taking global point cloud as input require accurate registration and ground truth coordinate labels, which limits their application scenarios. In this paper, we propose a new method that uses sparse LiDAR point clouds and rough odometry to reconstruct fine-grained implicit occupancy field efficiently within a few minutes. We introduce a new loss function that supervises directly in 3D space without 2D rendering, avoiding information loss. We also manage to refine poses of input frames in an end-to-end manner, creating consistent geometry without global point cloud registration. As far as we know, our method is the first to reconstruct implicit scene representation from LiDAR-only input. Experiments on synthetic and real-world datasets, including indoor and outdoor scenes, prove that our method is effective, efficient, and accurate, obtaining comparable results with existing methods using dense input.