Processing math: 100%
Dual-Branch Deep Point Cloud Registration Framework for Unconstrained Rotation | IEEE Journals & Magazine | IEEE Xplore

Dual-Branch Deep Point Cloud Registration Framework for Unconstrained Rotation


Abstract:

Learning-based rigid point cloud registration (RPCR) studies have made great progress recently but most existing methods have a small convergence region and can only be u...Show More

Abstract:

Learning-based rigid point cloud registration (RPCR) studies have made great progress recently but most existing methods have a small convergence region and can only be used to solve the registration problem with a small rotation angle, which is usually constrained within [0, 45^\circ ]. However, the relative rotation between point clouds is usually unconstrained in practice. To address this challenging problem, we propose a new RPCR network and integrate it into a new dual-branch registration framework for unconstrained rotation point cloud registration. The dual-branch framework consists of a large-rotation branch and a small-rotation branch, which are used to accurately register point clouds with large and small relative rotations, respectively. In addition, we propose a multiview intersection over the union module to select a better registration result from the output of the two branches. Extensive experiments on both ModelNet40 and MVP-RG datasets demonstrate that our proposed method outperforms existing state-of-the-art techniques by a large margin.
Published in: IEEE Transactions on Industrial Informatics ( Volume: 19, Issue: 7, July 2023)
Page(s): 7851 - 7861
Date of Publication: 20 October 2022

ISSN Information:

Funding Agency:


References

References is not available for this document.