A point cloud registration method and system based on a rotation equivariant network

By combining a point cloud registration method based on rotational isovariant networks with point and patch networks, an efficient feature learning framework and matching strategy are designed. This solves the problems of low efficiency and poor accuracy in point cloud registration in existing technologies, and improves the in-place ratio and generalization ability.

CN115953442BActive Publication Date: 2026-04-07SUN YAT SEN UNIVERSITY SHENZHEN +2
2 Cites 0 Cited by

Patent Information

Application Number
CN202310016404.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-01-06
Publication Date
2026-04-07
Estimated Expiration
2043-01-06

AI Technical Summary

Technical Problem

Existing point cloud registration methods struggle to balance efficiency, accuracy, and generalization, and lack effective matching mechanisms, resulting in low inlier rates that fail to meet practical application needs.

Method used

A rotation-invariant network-based approach is adopted, which combines point-based and patch-based networks. By extracting rotation-invariant and SO(2) equivariant features, a coarse-to-fine matching strategy is designed to generate point correspondences with high interior point ratios. The relative pose is then solved by a correspondence grouping algorithm.

Benefits of technology

It achieves efficient and accurate point cloud registration, improves the in-point rate and generalization ability, and can efficiently align point clouds in unknown scenarios.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application discloses a point cloud registration method and system based on a rotation equivariant network, and the method comprises the following steps: obtaining point clouds to be registered; processing each point cloud to be registered by using a first network based on point rotation equivariance and translation invariance, obtaining a reference direction and a key point score of each point cloud; extracting key points according to the key point score, and extracting a rotation invariant and SO(2) equivariant feature for each key point according to the reference direction and a second network based on patches; based on a preset matching strategy, generating point correspondences with a high inlier rate according to the features; and solving a relative pose by using a corresponding grouping algorithm according to the point correspondences, thereby completing point cloud registration. The embodiment of the application constructs an efficient and universal feature learning framework, can generate point correspondences with a high inlier rate by using rotation invariant and SO(2) equivariant features, and can be widely applied to the technical field of computers.
Need to check novelty before this filing date? Find Prior Art