Multi-view Point Cloud Registration based on Evolutionary Multitasking with Bi-Channel Knowledge Sharing Mechanism

TL;DR

This paper introduces a novel multi-task optimization framework with a bi-channel knowledge sharing mechanism to improve multi-view point cloud registration, enhancing accuracy and convergence speed in 3D reconstruction tasks.

Contribution

It models multi-view point cloud registration as multi-task optimization and proposes a bi-channel knowledge sharing mechanism for better solution quality and efficiency.

Findings

Effective in improving registration accuracy

Accelerates convergence speed

Handles complex multi-view registration scenarios

Abstract

Multi-view point cloud registration is fundamental in 3D reconstruction. Since there are close connections between point clouds captured from different viewpoints, registration performance can be enhanced if these connections be harnessed properly. Therefore, this paper models the registration problem as multi-task optimization, and proposes a novel bi-channel knowledge sharing mechanism for effective and efficient problem solving. The modeling of multi-view point cloud registration as multi-task optimization are twofold. By simultaneously considering the local accuracy of two point clouds as well as the global consistency posed by all the point clouds involved, a fitness function with an adaptive threshold is derived. Also a framework of the co-evolutionary search process is defined for the concurrent optimization of multiple fitness functions belonging to related tasks. To enhance solution quality and convergence speed, the proposed bi-channel knowledge sharing mechanism plays its role. The intra-task knowledge sharing introduces aiding tasks that are much simpler to solve, and useful information is shared across aiding tasks and the original tasks, accelerating the search process. The inter-task knowledge sharing explores commonalities buried among the original tasks, aiming to prevent tasks from getting stuck to local optima. Comprehensive experiments conducted on model object as well as scene point clouds show the efficacy of the proposed method.