English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

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 anefficient hierarchical network named HRegNet for large-scale outdoor LiDARpoint cloud registration. Instead of using all points in the point clouds,HRegNet performs registration on hierarchically extracted keypoints anddescriptors. The overall framework combines the reliable features in deeperlayer and the precise position information in shallower layers to achieverobust and precise registration. We present a correspondence network togenerate correct and accurate keypoints correspondences. Moreover, bilateralconsensus and neighborhood consensus are introduced for keypoints matching andnovel similarity features are designed to incorporate them into thecorrespondence network, which significantly improves the registrationperformance. Besides, the whole network is also highly efficient since only asmall number of keypoints are used for registration. Extensive experiments areconducted on two large-scale outdoor LiDAR point cloud datasets to demonstratethe high accuracy and efficiency of the proposed HRegNet. The project websiteis https://ispc-group.github.io/hregnet.

HRegNet: A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registration