Top-I2P

Explore Open-Domain Image-to-Point Cloud Registration Using Topology Relationship

Conference Paper (2025)
Author(s)

Pei An (Huazhong University of Science and Technology)

Jiaqi Yang (Northwestern Polytechnical University)

Muyao Peng (Huazhong University of Science and Technology)

You Yang (Huazhong University of Science and Technology)

Qiong Liu (Huazhong University of Science and Technology)

Jie Ma (Huazhong University of Science and Technology)

Liangliang Nan (TU Delft - Architecture and the Built Environment)

Research Group
Urban Data Science
DOI related publication
https://doi.org/10.24963/ijcai.2025/76 Final published version
More Info
expand_more
Publication Year
2025
Language
English
Research Group
Urban Data Science
Pages (from-to)
674-683
Publisher
International Joint Conferences on Artificial Intelligence
ISBN (electronic)
9781956792065
Event
34th Internationa Joint Conference on Artificial Intelligence, IJCAI 2025 (2025-08-16 - 2025-08-22), Montreal, Canada
Downloads counter
25
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Image-to-point cloud (I2P) registration is a fundamental task in computer vision, which aims to align pixels in 2D images with corresponding points in 3D point clouds. While deep learning based methods dominate this field, they often fail to generalize to the open domain. In this paper, we address open-domain I2P registration from the topology relationship perspective. Firstly, we find that topology relationship reflect sparse connections between pixels and points, which shows the significant potential in enhancing cross-modality feature interaction in the open domain. Building on this insight, we develop an I2P registration framework using topology relationship. After that, to construct and leverage the topology relationship between the heterogeneous 2D and 3D spaces, we design a registration network, Top-I2P, with correction-based topology reasoning and fast topology feature interaction modules. Extensive experiments on 7-Scenes, RGBD-V2, ScanNet, and self-collected I2P datasets demonstrate that Top-I2P achieves superior registration performance in open-domain scenarios.

Files

0076.pdf
(pdf | 9 Mb)
License info not available