Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.05060 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918437632081920 |
|---|---|
| author | Kashefbahrami, Yasaman Akdag, Erkut Meletis, Panagiotis Balmashnova, Evgeniya Goswami, Dip Bondarau, Egor |
| author_facet | Kashefbahrami, Yasaman Akdag, Erkut Meletis, Panagiotis Balmashnova, Evgeniya Goswami, Dip Bondarau, Egor |
| contents | Accurate Point Cloud Registration (PCR) is an important task in 3D data processing, involving the estimation of a rigid transformation between two point clouds. While deep-learning methods have addressed key limitations of traditional non-learning approaches, such as sensitivity to noise, outliers, occlusion, and initialization, they are developed and evaluated on clean, dense, synthetic datasets (limiting their generalizability to real-world industrial scenarios). This paper introduces R3PM-Net, a lightweight, global-aware, object-level point matching network designed to bridge this gap by prioritizing both generalizability and real-time efficiency. To support this transition, two datasets, Sioux-Cranfield and Sioux-Scans, are proposed. They provide an evaluation ground for registering imperfect photogrammetric and event-camera scans to digital CAD models, and have been made publicly available. Extensive experiments demonstrate that R3PM-Net achieves competitive accuracy with unmatched speed. On ModelNet40, it reaches a perfect fitness score of $1$ and inlier RMSE of $0.029$ cm in only $0.007$s, approximately 7 times faster than the state-of-the-art method RegTR. This performance carries over to the Sioux-Cranfield dataset, maintaining a fitness of $1$ and inlier RMSE of $0.030$ cm with similarly low latency. Furthermore, on the highly challenging Sioux-Scans dataset, R3PM-Net successfully resolves edge cases in under 50 ms. These results confirm that R3PM-Net offers a robust, high-speed solution for critical industrial applications, where precision and real-time performance are indispensable. The code and datasets are available at https://github.com/YasiiKB/R3PM-Net. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_05060 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | R3PM-Net: Real-time, Robust, Real-world Point Matching Network Kashefbahrami, Yasaman Akdag, Erkut Meletis, Panagiotis Balmashnova, Evgeniya Goswami, Dip Bondarau, Egor Computer Vision and Pattern Recognition Machine Learning Accurate Point Cloud Registration (PCR) is an important task in 3D data processing, involving the estimation of a rigid transformation between two point clouds. While deep-learning methods have addressed key limitations of traditional non-learning approaches, such as sensitivity to noise, outliers, occlusion, and initialization, they are developed and evaluated on clean, dense, synthetic datasets (limiting their generalizability to real-world industrial scenarios). This paper introduces R3PM-Net, a lightweight, global-aware, object-level point matching network designed to bridge this gap by prioritizing both generalizability and real-time efficiency. To support this transition, two datasets, Sioux-Cranfield and Sioux-Scans, are proposed. They provide an evaluation ground for registering imperfect photogrammetric and event-camera scans to digital CAD models, and have been made publicly available. Extensive experiments demonstrate that R3PM-Net achieves competitive accuracy with unmatched speed. On ModelNet40, it reaches a perfect fitness score of $1$ and inlier RMSE of $0.029$ cm in only $0.007$s, approximately 7 times faster than the state-of-the-art method RegTR. This performance carries over to the Sioux-Cranfield dataset, maintaining a fitness of $1$ and inlier RMSE of $0.030$ cm with similarly low latency. Furthermore, on the highly challenging Sioux-Scans dataset, R3PM-Net successfully resolves edge cases in under 50 ms. These results confirm that R3PM-Net offers a robust, high-speed solution for critical industrial applications, where precision and real-time performance are indispensable. The code and datasets are available at https://github.com/YasiiKB/R3PM-Net. |
| title | R3PM-Net: Real-time, Robust, Real-world Point Matching Network |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2604.05060 |