VRHCF: Cross-Source Point Cloud Registration via Voxel Representation and Hierarchical Correspondence Filtering
It addresses the challenge of registering point clouds from diverse sensors, which is crucial for applications like robotics and autonomous driving, but is incremental as it builds on existing registration methods.
The paper tackles the problem of robust cross-source point cloud registration by proposing a framework with spherical voxel feature representation and hierarchical correspondence filtering, achieving a 95.1% registration recall on homologous data and a 9.3 percentage point improvement on cross-source datasets.
Addressing the challenges posed by the substantial gap in point cloud data collected from diverse sensors, achieving robust cross-source point cloud registration becomes a formidable task. In response, we present a novel framework for point cloud registration with broad applicability, suitable for both homologous and cross-source registration scenarios. To tackle the issues arising from different densities and distributions in cross-source point cloud data, we introduce a feature representation based on spherical voxels. Furthermore, addressing the challenge of numerous outliers and mismatches in cross-source registration, we propose a hierarchical correspondence filtering approach. This method progressively filters out mismatches, yielding a set of high-quality correspondences. Our method exhibits versatile applicability and excels in both traditional homologous registration and challenging cross-source registration scenarios. Specifically, in homologous registration using the 3DMatch dataset, we achieve the highest registration recall of 95.1% and an inlier ratio of 87.8%. In cross-source point cloud registration, our method attains the best RR on the 3DCSR dataset, demonstrating a 9.3 percentage points improvement. The code is available at https://github.com/GuiyuZhao/VRHCF.