Learning to Register Unbalanced Point Pairs

07/09/2022
by   Kanghee Lee, et al.
0

Recent 3D registration methods can effectively handle large-scale or partially overlapping point pairs. However, despite its practicality, matching the unbalanced pairs in terms of spatial scale and density has been overlooked. We present a novel 3D registration method, called UPPNet, for the unbalanced point pairs. We propose a hierarchical framework to find inlier correspondences effectively by gradually reducing search space. Our method predicts the subregions of the target points likely to be overlapped with the query points. The following super-point matching module and fine-grained refinement module estimate accurate inlier correspondences between two point clouds. Furthermore, we apply geometric constraints to refine the correspondences that satisfy spatial compatibility. Correspondence prediction is trained end-to-end, and our approach can predict the proper rigid transformation with a single forward pass given unbalanced point cloud pairs. To validate the efficacy of the proposed method, we create a KITTI-UPP dataset by augmenting the KITTI LiDAR dataset. Experiments on this dataset reveal that the proposed approach significantly outperforms state-of-the-art pairwise point cloud registration methods by a large margin, resulting in 78 target point cloud is about 10× spatially larger and about 10× times denser than the query point cloud.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/30/2020

End-to-End 3D Point Cloud Learning for Registration Task Using Virtual Correspondences

3D Point cloud registration is still a very challenging topic due to the...
research
09/09/2021

Deep Hough Voting for Robust Global Registration

Point cloud registration is the task of estimating the rigid transformat...
research
02/12/2023

Large-scale Point Cloud Registration Based on Graph Matching Optimization

Point Clouds Registration is a fundamental and challenging problem in 3D...
research
07/03/2023

Direct Superpoints Matching for Fast and Robust Point Cloud Registration

Although deep neural networks endow the downsampled superpoints with dis...
research
10/26/2021

CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration

We study the problem of extracting correspondences between a pair of poi...
research
11/24/2020

Multi-Features Guidance Network for partial-to-partial point cloud registration

To eliminate the problems of large dimensional differences, big semantic...
research
03/22/2023

RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration

Although point cloud registration has achieved remarkable advances in ob...

Please sign up or login with your details

Forgot password? Click here to reset