Cascading Feature Extraction for Fast Point Cloud Registration

TL;DR

This paper introduces a cascading feature extraction method that accelerates 3D point cloud registration by reducing redundant computations, achieving about three times faster processing without sacrificing accuracy.

Contribution

The paper presents a novel cascading shallow layer approach that significantly speeds up point cloud registration by eliminating unnecessary feature extraction steps.

Findings

Approximately three times faster than existing methods

No loss in registration accuracy

Reduces computational cost significantly

Abstract

We propose a method for speeding up a 3D point cloud registration through a cascading feature extraction. The current approach with the highest accuracy is realized by iteratively executing feature extraction and registration using deep features. However, iterative feature extraction takes time. Our proposed method significantly reduces the computational cost using cascading shallow layers. Our idea is to omit redundant computations that do not always contribute to the final accuracy. The proposed approach is approximately three times faster than the existing methods without a loss of accuracy.