Multi-instance Point Cloud Registration by Efficient Correspondence Clustering

TL;DR

This paper introduces a fast and robust multi-instance point cloud registration method that clusters correspondences based on a distance invariance matrix, outperforming existing approaches especially with high outlier ratios.

Contribution

The proposed approach directly clusters noisy correspondences for multi-instance registration, improving robustness and efficiency over traditional hypothesis sampling methods.

Findings

Successfully registers up to 20 instances with high accuracy

Achieves at least 10x speedup compared to existing methods

Handles 70% outliers effectively

Abstract

We address the problem of estimating the poses of multiple instances of the source point cloud within a target point cloud. Existing solutions require sampling a lot of hypotheses to detect possible instances and reject the outliers, whose robustness and efficiency degrade notably when the number of instances and outliers increase. We propose to directly group the set of noisy correspondences into different clusters based on a distance invariance matrix. The instances and outliers are automatically identified through clustering. Our method is robust and fast. We evaluated our method on both synthetic and real-world datasets. The results show that our approach can correctly register up to 20 instances with an F1 score of 90.46% in the presence of 70% outliers, which performs significantly better and at least 10x faster than existing methods