A Single Correspondence Is Enough: Robust Global Registration to Avoid Degeneracy in Urban Environments
This addresses a critical issue for mobile platforms in urban environments needing reliable localization and loop-closing, though it is an incremental improvement over existing global registration methods.
The paper tackles the degeneracy problem in global 3D point cloud registration, where traditional methods fail when inlier correspondences drop below three, by proposing Quatro, a method that reduces the minimum degrees of freedom from three to one using quasi-SO(3) estimation under the Atlanta world assumption, achieving robust performance in indoor and outdoor LiDAR datasets even for distant point cloud pairs.
Global registration using 3D point clouds is a crucial technology for mobile platforms to achieve localization or manage loop-closing situations. In recent years, numerous researchers have proposed global registration methods to address a large number of outlier correspondences. Unfortunately, the degeneracy problem, which represents the phenomenon in which the number of estimated inliers becomes lower than three, is still potentially inevitable. To tackle the problem, a degeneracy-robust decoupling-based global registration method is proposed, called Quatro. In particular, our method employs quasi-SO(3) estimation by leveraging the Atlanta world assumption in urban environments to avoid degeneracy in rotation estimation. Thus, the minimum degree of freedom (DoF) of our method is reduced from three to one. As verified in indoor and outdoor 3D LiDAR datasets, our proposed method yields robust global registration performance compared with other global registration methods, even for distant point cloud pairs. Furthermore, the experimental results confirm the applicability of our method as a coarse alignment. Our code is available: https://github.com/url-kaist/quatro.