Cross-PCR: A Robust Cross-Source Point Cloud Registration Framework

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Guiyu, Guo, Zhentao, Du, Zewen, Ma, Hongbin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915080784838656
author Zhao, Guiyu
Guo, Zhentao
Du, Zewen
Ma, Hongbin
author_facet Zhao, Guiyu
Guo, Zhentao
Du, Zewen
Ma, Hongbin
contents Due to the density inconsistency and distribution difference between cross-source point clouds, previous methods fail in cross-source point cloud registration. We propose a density-robust feature extraction and matching scheme to achieve robust and accurate cross-source registration. To address the density inconsistency between cross-source data, we introduce a density-robust encoder for extracting density-robust features. To tackle the issue of challenging feature matching and few correct correspondences, we adopt a loose-to-strict matching pipeline with a ``loose generation, strict selection'' idea. Under it, we employ a one-to-many strategy to loosely generate initial correspondences. Subsequently, high-quality correspondences are strictly selected to achieve robust registration through sparse matching and dense matching. On the challenging Kinect-LiDAR scene in the cross-source 3DCSR dataset, our method improves feature matching recall by 63.5 percentage points (pp) and registration recall by 57.6 pp. It also achieves the best performance on 3DMatch, while maintaining robustness under diverse downsampling densities.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18873
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cross-PCR: A Robust Cross-Source Point Cloud Registration Framework
Zhao, Guiyu
Guo, Zhentao
Du, Zewen
Ma, Hongbin
Computer Vision and Pattern Recognition
Due to the density inconsistency and distribution difference between cross-source point clouds, previous methods fail in cross-source point cloud registration. We propose a density-robust feature extraction and matching scheme to achieve robust and accurate cross-source registration. To address the density inconsistency between cross-source data, we introduce a density-robust encoder for extracting density-robust features. To tackle the issue of challenging feature matching and few correct correspondences, we adopt a loose-to-strict matching pipeline with a ``loose generation, strict selection'' idea. Under it, we employ a one-to-many strategy to loosely generate initial correspondences. Subsequently, high-quality correspondences are strictly selected to achieve robust registration through sparse matching and dense matching. On the challenging Kinect-LiDAR scene in the cross-source 3DCSR dataset, our method improves feature matching recall by 63.5 percentage points (pp) and registration recall by 57.6 pp. It also achieves the best performance on 3DMatch, while maintaining robustness under diverse downsampling densities.
title Cross-PCR: A Robust Cross-Source Point Cloud Registration Framework
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.18873