Matching Distance and Geometric Distribution Aided Learning Multiview Point Cloud Registration

TL;DR

This paper introduces a novel neural network-based approach for multiview point cloud registration that leverages matching distance and geometric distribution information to improve pose graph construction and motion synchronization accuracy.

Contribution

It proposes new neural network models utilizing matching distance and geometric distribution for more reliable pose graph construction and motion synchronization in multiview point cloud registration.

Findings

Effective on diverse indoor and outdoor datasets

Improves reliability of pose graph construction

Enhances accuracy of motion synchronization

Abstract

Multiview point cloud registration plays a crucial role in robotics, automation, and computer vision fields. This paper concentrates on pose graph construction and motion synchronization within multiview registration. Previous methods for pose graph construction often pruned fully connected graphs or constructed sparse graph using global feature aggregated from local descriptors, which may not consistently yield reliable results. To identify dependable pairs for pose graph construction, we design a network model that extracts information from the matching distance between point cloud pairs. For motion synchronization, we propose another neural network model to calculate the absolute pose in a data-driven manner, rather than optimizing inaccurate handcrafted loss functions. Our model takes into account geometric distribution information and employs a modified attention mechanism to facilitate flexible and reliable feature interaction. Experimental results on diverse indoor and outdoor datasets confirm the effectiveness and generalizability of our approach. The source code is available at https://github.com/Shi-Qi-Li/MDGD.