FF-LOGO: Cross-Modality Point Cloud Registration with Feature Filtering and Local to Global Optimization

TL;DR

This paper introduces FF-LOGO, a novel cross-modality point cloud registration framework that employs feature filtering and local-global optimization to improve registration accuracy across different sensor modalities.

Contribution

The paper presents a new framework with feature correlation filtering and a two-stage optimization process for enhanced cross-modality point cloud registration.

Findings

Significantly improves registration accuracy.

Increases recall rate from 40.59% to 75.74%.

Outperforms current state-of-the-art methods.

Abstract

Cross-modality point cloud registration is confronted with significant challenges due to inherent differences in modalities between different sensors. We propose a cross-modality point cloud registration framework FF-LOGO: a cross-modality point cloud registration method with feature filtering and local-global optimization. The cross-modality feature correlation filtering module extracts geometric transformation-invariant features from cross-modality point clouds and achieves point selection by feature matching. We also introduce a cross-modality optimization process, including a local adaptive key region aggregation module and a global modality consistency fusion optimization module. Experimental results demonstrate that our two-stage optimization significantly improves the registration accuracy of the feature association and selection module. Our method achieves a substantial increase in recall rate compared to the current state-of-the-art methods on the 3DCSR dataset, improving from 40.59% to 75.74%. Our code will be available at https://github.com/wangmohan17/FFLOGO.