Unsupervised Point Cloud Registration via Salient Points Analysis (SPA)

TL;DR

This paper introduces SPA, an unsupervised point cloud registration method that uses salient points and local surface features, offering a lightweight alternative to deep learning approaches.

Contribution

The paper presents SPA, a novel unsupervised registration technique based on salient points analysis, reducing training time and model size compared to deep learning methods.

Findings

SPA effectively registers point clouds with fewer salient points.

SPA outperforms some deep learning methods on ModelNet-40.

SPA works well on noisy and unseen class point clouds.

Abstract

An unsupervised point cloud registration method, called salient points analysis (SPA), is proposed in this work. The proposed SPA method can register two point clouds effectively using only a small subset of salient points. It first applies the PointHop++ method to point clouds, finds corresponding salient points in two point clouds based on the local surface characteristics of points and performs registration by matching the corresponding salient points. The SPA method offers several advantages over the recent deep learning based solutions for registration. Deep learning methods such as PointNetLK and DCP train end-to-end networks and rely on full supervision (namely, ground truth transformation matrix and class label). In contrast, the SPA is completely unsupervised. Furthermore, SPA's training time and model size are much less. The effectiveness of the SPA method is demonstrated by experiments on seen and unseen classes and noisy point clouds from the ModelNet-40 dataset.