DMS: Low-overlap Registration of 3D Point Clouds with Double-layer Multi-scale Star-graph

IEEE Transactions on Visualization and Computer Graphics

Hualong Cao 1, Yongcai Wang1, Deying Li1

1School of Information, Renmin University of China, Beijing, 100872

 

image-20240529183359317 image-20240529183422179

 

 

Overview

Registering 3D point clouds with low overlap is challenging in 3D computer vision, primarily due to difficulties in identifying small overlap regions and removing correspondence outliers. We observe that the neighborhood similarity can be utilized to detect point correspondence, and the consistent neighborhood correspondence can be used as a criterion to detect robust overlapping regions. So that a Double-layer Multi-scale Star-graph (DMS) structure is proposed to detect robust correspondences using two different types of multi-scale star-graphs. The first-layer \emph{Multi-scale Neighbor Feature Star-graphs} (MNFS) takes each point as the center and its multi-scale nearest neighbors as the leaves. The MNFS enables to establish the initial correspondence candidate set between the two point clouds based on multi-scale neighborhood topology and feature similarity. Subsequently, each pair of corresponding points find their nearest neighbors within the correspondence sets to construct a Multi-scale Matching Star-graphs (MMS) on each side, so the mutual correspondence relationships between the MMS vertices are identified. These identified mutual correspondences are treated as vertices to construct the \emph{Multi-scale Correspondence Star-graphs (MCS)} , that indicate the relationships among the correspondences. We design edge weight and vertex weight criterion in MCS to detect only the robust correspondence set that has strong neighborhood consistency, so as to reject the outliers. Finally, the point cloud registration is conducted based on the detected robust correspondence. The experimental results demonstrate clearly that the proposed DMS method exhibits superior robustness when compared to existing state-of-the-art registration algorithms.

System Architecture

Each agent uses its own sensor information to perform points and lines VIO and then transmits the results to the server through a communication module. The server stores the information of the agent through map caching. The server performs place recognition, map fusion, and optimization based on point and line features. Then, the pose drifts are transmitted to the agents for correcting the agents’ local drifts.

 

1

Contributions

 

Evaluations

 

2

3

4

5

Bibtex

Acknowledgment

Dr. Wang is supported in part by the National Natural Science Foundation of China Grant No. 61972404, Public Computing Cloud, Renmin University of China, and the Blockchain Lab. School of Information, Renmin University of China. Dr. Li is supported in part by the National Natural Science Foundation of China Grant No. 12071478. Hualong Cao is supported by the Fundamental Research Funds for the Central Universities, and the Research Funds of Renmin University of China Grant No. 23XNH146, and Supported by the Outstanding Innovative Talents Cultivation Funded Programs 2023 of Renmin University of China.