What does this research mean for the field?

An Attention and Mamba-based iterative registration network improves point cloud registration performance in low-overlap scenarios and reduces computational complexity for large-scale point clouds compared to transformer-based methods. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The research aims to improve point cloud registration performance in low-overlap conditions while addressing high computational costs in large-scale scenarios.

May 20, 2026Computers, materials & continua/Computers, materials & continua (Print)0 citationsOpen Access

Attention and Mamba Based Iterative Registration Network for Low-Overlap and Large-Scale Point Cloud

HCHaotian CaoMichigan Department of Transportation QZQingsheng ZhuUniversity of Southern California

Key Points

The research aims to improve point cloud registration performance in low-overlap conditions while addressing high computational costs in large-scale scenarios.
Developed a novel registration network utilizing attention mechanisms and Mamba algorithms.
Evaluated performance across different overlap scenarios and computational demands.
Compared the proposed method against existing transformer-based approaches.
Demonstrated improved registration performance in low-overlap situations.
Reduced computational resource consumption when handling large-scale point clouds.
Achieved significant efficiency gains compared to conventional methods.

Abstract

Point Cloud Registration (PCR) is a basic task in computer vision, mobile robotics, and autonomous driving. PCR primarily faces challenges, including insufficient registration performance in low-overlap scenarios and high computational resource consumption in large-scale point cloud scenarios. Most recent PCR methods are transformer-based. Methods like transformers have quadratic computational complexity

KI fragen

Bookmark

View Full Paper