K-means clustering for efficient and robust registration of multi-view point sets

TL;DR

This paper introduces a novel multi-view point set registration method that uses k-means clustering to improve efficiency and robustness, making it suitable for real-time applications.

Contribution

The paper proposes a clustering-based registration approach that enhances efficiency and robustness by iteratively updating cluster centroids and transformations.

Findings

Validated on benchmark datasets showing improved robustness

Achieved higher efficiency compared to existing methods

Demonstrated stability in multi-view registration tasks

Abstract

Generally, there are three main factors that determine the practical usability of registration, i.e., accuracy, robustness, and efficiency. In real-time applications, efficiency and robustness are more important. To promote these two abilities, we cast the multi-view registration into a clustering task. All the centroids are uniformly sampled from the initially aligned point sets involved in the multi-view registration, which makes it rather efficient and effective for the clustering. Then, each point is assigned to a single cluster and each cluster centroid is updated accordingly. Subsequently, the shape comprised by all cluster centroids is used to sequentially estimate the rigid transformation for each point set. For accuracy and stability, clustering and transformation estimation are alternately and iteratively applied to all point sets. We tested our proposed approach on several benchmark datasets and compared it with state-of-the-art approaches. Experimental results validate its efficiency and robustness for the registration of multi-view point sets.