Score: 0

Generative Point Cloud Registration

Published: December 10, 2025 | arXiv ID: 2512.09407v1

By: Haobo Jiang , Jin Xie , Jian Yang and more

Potential Business Impact:

Helps 3D scans match up better.

Business Areas:
Image Recognition Data and Analytics, Software

In this paper, we propose a novel 3D registration paradigm, Generative Point Cloud Registration, which bridges advanced 2D generative models with 3D matching tasks to enhance registration performance. Our key idea is to generate cross-view consistent image pairs that are well-aligned with the source and target point clouds, enabling geometry-color feature fusion to facilitate robust matching. To ensure high-quality matching, the generated image pair should feature both 2D-3D geometric consistency and cross-view texture consistency. To achieve this, we introduce Match-ControlNet, a matching-specific, controllable 2D generative model. Specifically, it leverages the depth-conditioned generation capability of ControlNet to produce images that are geometrically aligned with depth maps derived from point clouds, ensuring 2D-3D geometric consistency. Additionally, by incorporating a coupled conditional denoising scheme and coupled prompt guidance, Match-ControlNet further promotes cross-view feature interaction, guiding texture consistency generation. Our generative 3D registration paradigm is general and could be seamlessly integrated into various registration methods to enhance their performance. Extensive experiments on 3DMatch and ScanNet datasets verify the effectiveness of our approach.

Country of Origin
πŸ‡ΈπŸ‡¬ Singapore

Page Count
14 pages

Category
Computer Science:
CV and Pattern Recognition