Zhao Zeng

Existing point cloud registration methods can effectively handle large-scale and partially overlapping point cloud pairs. However, registering unbalanced point cloud pairs with significant disparities in spatial extent and point density remains a challenging problem that has received limited research attention. This challenge primarily arises from the difficulty in achieving accurate local registration when the point clouds exhibit substantial scale variations and uneven density distributions. This paper presents a novel registration method for unbalanced point cloud pairs that utilizes the local point cluster structure feature for effective outlier rejection. The fundamental principle underlying our method is that the internal structure of a local cluster comprising a point and its K-nearest neighbors maintains rigidity-preserved invariance across different point clouds. The proposed pipeline operates through four sequential stages. First, keypoints are detected in both the source and target point clouds. Second, local feature descriptors are employed to establish initial one-to-many correspondences, which is a strategy that increases correspondences redundancy to enhance the pool of potential inliers. Third, the proposed Local Point Cluster Structure Feature is applied to filter outliers from the initial correspondences. Finally, the transformation hypothesis is generated and evaluated through the RANSAC method. To validate the efficacy of the proposed method, we construct a carefully designed benchmark named KITTI-UPP (KITTI-Unbalanced Point cloud Pairs) based on the KITTI odometry dataset. We further evaluate our method on the real-world TIESY Dataset which is a LiDAR-scanned dataset collected by the Third Railway Survey and Design Institute Group Co. Extensive experiments demonstrate that our method significantly outperforms the state-of-the-art methods in terms of both registration success rate and computational efficiency on the KITTI-UPP benchmark. Moreover, it achieves competitive results on the real-world TIESY dataset, confirming its applicability and generalizability across diverse real-world scenarios.

Obtaining highly consistent correspondences between point clouds is crucial for computer vision tasks such as 3D registration and recognition. Due to nuisances such as limited overlap and noise, initial correspondences often contain a large number of outliers, imposing a great challenge to downstream tasks. In this paper, we present a novel single voter spreading (SVOS) method for efficient 3D correspondence grouping and 3D registration. Our core insight is to leverage low-order graph constraints only in a single voter spreading voting scheme to achieve comparable constrain-ability as complex constraints without searching them. First, a simple first-order graph is constructed for the initial correspondence set. Second, a two-stage voting method is proposed, including single voter voting and spread voters voting. Each voting stage involves both local and global voting via edge constraints only. This promises good selectivity while making the voting process time- and storage-efficient. Finally, top-scored correspondences are opted for robust transformation estimation. Experiments on U3M, 3DMatch/3DLoMatch, ETH, and KITTI-LC datasets verify that SVOS achieves new state-of-the-art correspondence grouping and registration performance, while being light-weight and robust to graph construction parameters.