RegiFormer: Unsupervised Point Cloud Registration via Geometric Local-to-Global Transformer and Self-Augmentation | IEEE Journals & Magazine | IEEE Xplore

RegiFormer: Unsupervised Point Cloud Registration via Geometric Local-to-Global Transformer and Self-Augmentation


Abstract:

Representation learning for two partially overlapping point clouds remains an open challenge in unsupervised point cloud registration (U-PCR). In this article, we introdu...Show More

Abstract:

Representation learning for two partially overlapping point clouds remains an open challenge in unsupervised point cloud registration (U-PCR). In this article, we introduce RegiFormer, a geometric local-to-global transformer (GLGT)-based unsupervised framework equipped with a self-augmentation (SA) strategy, for point cloud registration. The GLGT not only aggregates features from local neighborhoods but also extracts global intrarelationships within the entire point cloud using a transformation-invariant geometry embedding. In addition, it enhances the interrelationships between paired point clouds. To overcome the limited ability of U-PCR methods to learn alignment knowledge, we design an SA strategy that can be flexibly integrated into advanced models, significantly boosting their registration performance. Extensive experiments, conducted on five popular synthetic and real-scanned benchmarks, demonstrate the superior performance of RegiFormer compared to state-of-the-art methods, both qualitatively and quantitatively.
Article Sequence Number: 5705313
Date of Publication: 29 July 2024

ISSN Information:

Funding Agency:


References

References is not available for this document.