Enhance Image-to-Point-Cloud Registration with Beltrami Flow

Journal Article (2025)
Author(s)

Pei Chen (Huazhong University of Science and Technology)

You Yang (Huazhong University of Science and Technology)

Jiaqi Yang (Northwestern Polytechnical University)

Muyao Peng (Huazhong University of Science and Technology)

Qiong Liu (Huazhong University of Science and Technology)

Liangliang Nan (TU Delft - Urban Data Science)

Research Group
Urban Data Science
DOI related publication
https://doi.org/10.1007/s11263-025-02575-4
More Info
expand_more
Publication Year
2025
Language
English
Research Group
Urban Data Science
Bibliographical Note
Green Open Access added to TU Delft Institutional Repository as part of the Taverne amendment. More information about this copyright law amendment can be found at https://www.openaccess.nl. Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.@en
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 yet challenging problem in computer vision. Despite significant advances in deep learning, I2P registration struggles with correspondence accuracy when training samples are limited. To address this challenge, we propose a Beltrami flow based I2P registration method termed Flow-I2P. From the perspective of information geometry, I2P registration can be reframed as a manifold alignment problem. Our in-depth analysis shows that Beltrami flow enhances I2P registration by improving manifold alignment quality. Building on this analysis, we introduce a Beltrami flow based cross-modality feature interaction layer, B-flow, to progressively refine manifold alignment. To reduce memory and computation demands, B-flow is then optimized into C-flow through the incorporation of feature covariance-based attention. We further enhance I2P registration performance by developing Flow-I2P, which incorporates normal features, stacked C-flow layers, and a two-stage training strategy. To evaluate the registration performance of Flow-I2P, we conduct extensive experiments on five indoor and outdoor datasets, including RGB-D V2, 7-Scenes, ScanNet, KITTI, and a self-collected dataset. Our results indicate that Flow-I2P achieves higher inlier ratio (IR) and registration recall (RR) compared to state-of-the-art methods. We conclude that Flow-I2P significantly enhances I2P registration with superior capabilities.

Files

S11263-025-02575-4.pdf
(pdf | 14.4 Mb)
License info not available
warning

File under embargo until 19-03-2026