HRegNet: A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registration
Fan Lu, Guang Chen, Yinlong Liu, Lijun Zhang, Sanqing Qu, Shu Liu,, Rongqi Gu

TL;DR
HRegNet is a hierarchical neural network designed for efficient and accurate registration of large-scale outdoor LiDAR point clouds, leveraging keypoints and novel similarity features to improve robustness and speed.
Contribution
The paper introduces HRegNet, a hierarchical network that performs point cloud registration using keypoints and a novel correspondence matching approach, enhancing accuracy and efficiency over existing methods.
Findings
Achieves high registration accuracy on large-scale outdoor LiDAR datasets.
Demonstrates significant efficiency improvements by using fewer keypoints.
Outperforms existing methods in robustness and speed.
Abstract
Point cloud registration is a fundamental problem in 3D computer vision. Outdoor LiDAR point clouds are typically large-scale and complexly distributed, which makes the registration challenging. In this paper, we propose an efficient hierarchical network named HRegNet for large-scale outdoor LiDAR point cloud registration. Instead of using all points in the point clouds, HRegNet performs registration on hierarchically extracted keypoints and descriptors. The overall framework combines the reliable features in deeper layer and the precise position information in shallower layers to achieve robust and precise registration. We present a correspondence network to generate correct and accurate keypoints correspondences. Moreover, bilateral consensus and neighborhood consensus are introduced for keypoints matching and novel similarity features are designed to incorporate them into the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
Topics3D Shape Modeling and Analysis · Advanced Neural Network Applications · Human Pose and Action Recognition
