Learning to Register Unbalanced Point Pairs

TL;DR

UPPNet is a novel hierarchical deep learning approach for registering unbalanced point cloud pairs, effectively handling partial overlaps and varying densities, and it outperforms existing methods on multiple benchmarks.

Contribution

The paper introduces UPPNet, a hierarchical framework for unbalanced point cloud registration, and creates the KITTI-UPP benchmark dataset for evaluation.

Findings

Outperforms state-of-the-art methods on KITTI-UPP benchmark.

Achieves competitive results on standard registration benchmarks.

Effective in handling unbalanced and partially overlapping point clouds.

Abstract

Point cloud registration methods can effectively handle large-scale, partially overlapping point cloud pairs. Despite its practicality, matching the unbalanced pairs in terms of spatial extent and density has been overlooked and rarely studied. We present a novel method, dubbed UPPNet, for Unbalanced Point cloud Pair registration. We propose to incorporate a hierarchical framework that effectively finds inlier correspondences by gradually reducing search space. The proposed method first predicts subregions within target point cloud that are likely to be overlapped with query. Then following super-point matching and fine-grained refinement modules predict accurate inlier correspondences between the target and query. Additional geometric constraints are applied to refine the correspondences that satisfy spatial compatibility. The proposed network can be trained in an end-to-end manner, predicting the accurate rigid transformation with a single forward pass. To validate the efficacy of the proposed method, we create a carefully designed benchmark, named KITTI-UPP dataset, by augmenting the KITTI odometry dataset. Extensive experiments reveal that the proposed method not only outperforms state-of-the-art point cloud registration methods by large margins on KITTI-UPP benchmark, but also achieves competitive results on the standard pairwise registration benchmark including 3DMatch, 3DLoMatch, ScanNet, and KITTI, thus showing the applicability of our method on various datasets. The source code and dataset will be publicly released.