Point Cloud Registration using Representative Overlapping Points

TL;DR

This paper introduces ROPNet, a deep learning model that improves 3D point cloud registration by focusing on representative overlapping points, effectively handling partial overlaps and outperforming existing methods.

Contribution

The paper presents ROPNet, a novel deep learning approach that transforms partial-to-partial registration into partial-to-complete registration using a context-guided module and Transformer-based feature enrichment.

Findings

Outperforms traditional and learning-based methods on ModelNet40.

Achieves state-of-the-art registration accuracy.

Effectively handles noisy and partial overlaps.

Abstract

3D point cloud registration is a fundamental task in robotics and computer vision. Recently, many learning-based point cloud registration methods based on correspondences have emerged. However, these methods heavily rely on such correspondences and meet great challenges with partial overlap. In this paper, we propose ROPNet, a new deep learning model using Representative Overlapping Points with discriminative features for registration that transforms partial-to-partial registration into partial-to-complete registration. Specifically, we propose a context-guided module which uses an encoder to extract global features for predicting point overlap score. To better find representative overlapping points, we use the extracted global features for coarse alignment. Then, we introduce a Transformer to enrich point features and remove non-representative points based on point overlap score and feature matching. A similarity matrix is built in a partial-to-complete mode, and finally, weighted SVD is adopted to estimate a transformation matrix. Extensive experiments over ModelNet40 using noisy and partially overlapping point clouds show that the proposed method outperforms traditional and learning-based methods, achieving state-of-the-art performance. The code is available at https://github.com/zhulf0804/ROPNet.