Saved in:
Bibliographic Details
Main Authors: Cheng, Zhixin, Deng, Jiacheng, Li, Xinjun, Yin, Xiaotian, Liao, Bohao, Yin, Baoqun, Yang, Wenfei, Zhang, Tianzhu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.21364
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911024584589312
author Cheng, Zhixin
Deng, Jiacheng
Li, Xinjun
Yin, Xiaotian
Liao, Bohao
Yin, Baoqun
Yang, Wenfei
Zhang, Tianzhu
author_facet Cheng, Zhixin
Deng, Jiacheng
Li, Xinjun
Yin, Xiaotian
Liao, Bohao
Yin, Baoqun
Yang, Wenfei
Zhang, Tianzhu
contents Detection-free methods typically follow a coarse-to-fine pipeline, extracting image and point cloud features for patch-level matching and refining dense pixel-to-point correspondences. However, differences in feature channel attention between images and point clouds may lead to degraded matching results, ultimately impairing registration accuracy. Furthermore, similar structures in the scene could lead to redundant correspondences in cross-modal matching. To address these issues, we propose Channel Adaptive Adjustment Module (CAA) and Global Optimal Selection Module (GOS). CAA enhances intra-modal features and suppresses cross-modal sensitivity, while GOS replaces local selection with global optimization. Experiments on RGB-D Scenes V2 and 7-Scenes demonstrate the superiority of our method, achieving state-of-the-art performance in image-to-point cloud registration.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21364
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selection
Cheng, Zhixin
Deng, Jiacheng
Li, Xinjun
Yin, Xiaotian
Liao, Bohao
Yin, Baoqun
Yang, Wenfei
Zhang, Tianzhu
Computer Vision and Pattern Recognition
Artificial Intelligence
Detection-free methods typically follow a coarse-to-fine pipeline, extracting image and point cloud features for patch-level matching and refining dense pixel-to-point correspondences. However, differences in feature channel attention between images and point clouds may lead to degraded matching results, ultimately impairing registration accuracy. Furthermore, similar structures in the scene could lead to redundant correspondences in cross-modal matching. To address these issues, we propose Channel Adaptive Adjustment Module (CAA) and Global Optimal Selection Module (GOS). CAA enhances intra-modal features and suppresses cross-modal sensitivity, while GOS replaces local selection with global optimization. Experiments on RGB-D Scenes V2 and 7-Scenes demonstrate the superiority of our method, achieving state-of-the-art performance in image-to-point cloud registration.
title CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2506.21364