Multi-view 3D point cloud registration method based on generated multi-scale information granules

Chen Yang

doi:10.1016/j.displa.2026.103372

Multi-view 3D point cloud registration method based on generated multi-scale information granules

2026-02-04

0

PRE

AI

DOI：10.1016/j.displa.2026.103372

Original

Original request for help

Save

Abstract

En 中文

• Enhancing point cloud expression via FPFH-based information granules. • Removing outliers and weak curvature regions via FCM-based complexity thresholds. • Solving uneven overlap and noise mismatches via multi-view registration. • Improving accuracy via a hierarchical GMM framework for granule alignment. • Using EM algorithm to dynamically adjust granule size in real time.

Keywords:

FPFH-based information granules

FCM-based complexity thresholds

multi-view registration

hierarchical GMM framework

EM algorithm

Multi-view 3D point cloud registration method based on generated multi-scale information granules

Abstract

Journal

Organization