Saved in:
Bibliographic Details
Main Authors: Cheng, Zhixin, Deng, Jiacheng, Li, Xinjun, Yin, Baoqun, Zhang, Tianzhu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.01641
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916687228436480
author Cheng, Zhixin
Deng, Jiacheng
Li, Xinjun
Yin, Baoqun
Zhang, Tianzhu
author_facet Cheng, Zhixin
Deng, Jiacheng
Li, Xinjun
Yin, Baoqun
Zhang, Tianzhu
contents The method for image-to-point cloud registration typically determines the rigid transformation using a coarse-to-fine pipeline. However, directly and uniformly matching image patches with point cloud patches may lead to focusing on incorrect noise patches during matching while ignoring key ones. Moreover, due to the significant differences between image and point cloud modalities, it may be challenging to bridge the domain gap without specific improvements in design. To address the above issues, we innovatively propose the Uncertainty-aware Hierarchical Matching Module (UHMM) and the Adversarial Modal Alignment Module (AMAM). Within the UHMM, we model the uncertainty of critical information in image patches and facilitate multi-level fusion interactions between image and point cloud features. In the AMAM, we design an adversarial approach to reduce the domain gap between image and point cloud. Extensive experiments and ablation studies on RGB-D Scene V2 and 7-Scenes benchmarks demonstrate the superiority of our method, making it a state-of-the-art approach for image-to-point cloud registration tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2504_01641
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bridge 2D-3D: Uncertainty-aware Hierarchical Registration Network with Domain Alignment
Cheng, Zhixin
Deng, Jiacheng
Li, Xinjun
Yin, Baoqun
Zhang, Tianzhu
Computer Vision and Pattern Recognition
Artificial Intelligence
The method for image-to-point cloud registration typically determines the rigid transformation using a coarse-to-fine pipeline. However, directly and uniformly matching image patches with point cloud patches may lead to focusing on incorrect noise patches during matching while ignoring key ones. Moreover, due to the significant differences between image and point cloud modalities, it may be challenging to bridge the domain gap without specific improvements in design. To address the above issues, we innovatively propose the Uncertainty-aware Hierarchical Matching Module (UHMM) and the Adversarial Modal Alignment Module (AMAM). Within the UHMM, we model the uncertainty of critical information in image patches and facilitate multi-level fusion interactions between image and point cloud features. In the AMAM, we design an adversarial approach to reduce the domain gap between image and point cloud. Extensive experiments and ablation studies on RGB-D Scene V2 and 7-Scenes benchmarks demonstrate the superiority of our method, making it a state-of-the-art approach for image-to-point cloud registration tasks.
title Bridge 2D-3D: Uncertainty-aware Hierarchical Registration Network with Domain Alignment
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2504.01641