As a long-standing research issue in computer vision and robotics, multi-view registration has attracted much attention in recent years. Most existing works are mainly focus on the estimating the point to point match correspondence, which usually suffers from the poor initial pose and data noise as well as leads to the inaccurate matches. To overcome the aforementioned limitation, we propose a novel Hierarchical K-means Clustering Registration (HKCR), which casts the multi-view registration as a hierarchical clustering task. Specifically, the proposed method employs a small number of clusters firstly, then increases the number of clusters during the registration process. Benefiting from the recursive partitioning process, more robust and more accurate results can be achieved with the increasing finer granularity. To show the effectiveness and robustness of HKCR, extensive experiments are conducted on several benchmark datasets and compared to several state-of-the-art methods.

作为计算机视觉和机器人技术中长期存在的研究问题，多视图配准近年来备受关注。大多数现有工作主要集中在估计点对点匹配对应上，这通常会受到初始姿态和数据噪声不佳以及导致匹配不准确的影响。为了克服上述限制，我们提出了一种新颖的分层 K 均值聚类注册 (HKCR)，它将多视图注册转换为分层聚类任务。具体来说，所提出的方法首先使用少量的集群，然后在注册过程中增加集群的数量。受益于递归分区过程，随着粒度的增加，可以获得更健壮和更准确的结果。