End-to-End 3D Point Cloud Learning for Registration Task Using Virtual Correspondences

TL;DR

This paper introduces an end-to-end deep learning approach for 3D point cloud registration that leverages feature extraction, attention mechanisms, and virtual correspondences to improve accuracy and robustness in challenging scenarios.

Contribution

It presents a novel combination of a revised LPD-Net, attention mechanisms, and a soft pointer method to enhance point cloud registration without initial estimates.

Findings

Achieves state-of-the-art results on ModelNet40 dataset.

Validates effectiveness on real-world KITTI dataset.

Demonstrates robustness in partial and unestimated registration scenarios.

Abstract

3D Point cloud registration is still a very challenging topic due to the difficulty in finding the rigid transformation between two point clouds with partial correspondences, and it's even harder in the absence of any initial estimation information. In this paper, we present an end-to-end deep-learning based approach to resolve the point cloud registration problem. Firstly, the revised LPD-Net is introduced to extract features and aggregate them with the graph network. Secondly, the self-attention mechanism is utilized to enhance the structure information in the point cloud and the cross-attention mechanism is designed to enhance the corresponding information between the two input point clouds. Based on which, the virtual corresponding points can be generated by a soft pointer based method, and finally, the point cloud registration problem can be solved by implementing the SVD method. Comparison results in ModelNet40 dataset validate that the proposed approach reaches the state-of-the-art in point cloud registration tasks and experiment resutls in KITTI dataset validate the effectiveness of the proposed approach in real applications.Our source code is available at \url{https://github.com/qiaozhijian/VCR-Net.git}