HybridPoint: Point Cloud Registration Based on Hybrid Point Sampling and Matching

Yiheng Li, Canhui Tang, Runzhao Yao, Aixue Ye, Feng Wen +1 more
3/29/2023
cs.CV

Official code: liyih/HybridPoint (29 stars, MIT, last commit 2024-03-14).

Abstract

Patch-to-point matching has become a robust way of point cloud registration. However, previous patch-matching methods employ superpoints with poor localization precision as nodes, which may lead to ambiguous patch partitions. In this paper, we propose a HybridPoint-based network to find more robust and accurate correspondences. Firstly, we propose to use salient points with prominent local features as nodes to increase patch repeatability, and introduce some uniformly distributed points to complete the point cloud, thus constituting hybrid points. Hybrid points not only have better localization precision but also give a complete picture of the whole point cloud. Furthermore, based on the characteristic of hybrid points, we propose a dual-classes patch matching module, which leverages the matching results of salient points and filters the matching noise of non-salient points. Experiments show that our model achieves state-of-the-art performance on 3DMatch, 3DLoMatch, and KITTI odometry, especially with 93.0% Registration Recall on the 3DMatch dataset. Our code and models are available at https://github.com/liyih/HybridPoint.

View on arXivView PDF

Code Implementations(1)

liyih/HybridPointOfficial100%
MIT

[ICME 2023, Oral] HybridPoint: Point cloud registration based on hybrid point sampling and matching

292PythonMar 25, 20232 years agoMIT
coarse-to-finedeep-learninglidar-point-cloudpatch-to-pointpoint-cloud-registration+1 more

Similar Papers

BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration

86% match1 repo972023

GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer

86% match1 repo9752023

A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registration

86% match1 repo642024

GLASS: Geometry-aware Local Alignment and Structure Synchronization Network for 2D-3D Registration

85% match2026

Learning to Register Unbalanced Point Pairs

85% match2022

RPM-Net: Robust Point Matching using Learned Features

84% match1 repo4272020

Cite this paper

@article{li2023hybridpoint,
  title  = {HybridPoint: Point Cloud Registration Based on Hybrid Point Sampling and Matching},
  author = {Yiheng Li and Canhui Tang and Runzhao Yao and Aixue Ye and Feng Wen and Shaoyi Du},
  year   = {2023},
  eprint = {2303.16526},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2303.16526v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2303.16526.svg)](https://codeofpaper.com/paper/2303.16526)

Discussion