LPRnet: A self-supervised registration network for LiDAR and photogrammetric point clouds

TL;DR

This paper introduces a self-supervised registration network using a masked autoencoder and transformer architecture to accurately align heterogeneous LiDAR and photogrammetric point clouds without ground truth data.

Contribution

It presents a novel multi-scale masked training strategy and a rotation-translation embedding module for robust feature extraction and precise registration of diverse point clouds.

Findings

Effective registration of heterogeneous point clouds demonstrated on real-world datasets.

Robust feature extraction capabilities for LiDAR and photogrammetric data.

Improved alignment accuracy without requiring ground truth.

Abstract

LiDAR and photogrammetry are active and passive remote sensing techniques for point cloud acquisition, respectively, offering complementary advantages and heterogeneous. Due to the fundamental differences in sensing mechanisms, spatial distributions and coordinate systems, their point clouds exhibit significant discrepancies in density, precision, noise, and overlap. Coupled with the lack of ground truth for large-scale scenes, integrating the heterogeneous point clouds is a highly challenging task. This paper proposes a self-supervised registration network based on a masked autoencoder, focusing on heterogeneous LiDAR and photogrammetric point clouds. At its core, the method introduces a multi-scale masked training strategy to extract robust features from heterogeneous point clouds under self-supervision. To further enhance registration performance, a rotation-translation embedding module is designed to effectively capture the key features essential for accurate rigid transformations. Building upon the robust representations, a transformer-based architecture seamlessly integrates local and global features, fostering precise alignment across diverse point cloud datasets. The proposed method demonstrates strong feature extraction capabilities for both LiDAR and photogrammetric point clouds, addressing the challenges of acquiring ground truth at the scene level. Experiments conducted on two real-world datasets validate the effectiveness of the proposed method in solving heterogeneous point cloud registration problems.