2022/03/13 by Hyungtae Lim, Lim, Hyungtae, Suyong Yeon +15 · 5 citations
Earth and Planetary Sciences · Engineering · Environmental Science · #3D Surveying and Cultural Heritage #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Remote Sensing and LiDAR Applications #Robotics (cs.RO) #Robotics and Sensor-Based Localization
paper · pdf · doi:10.48550/arxiv.2203.06612
openalex publication_date 2022/03/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Global registration using 3D point clouds is a crucial technology for mobile\nplatforms to achieve localization or manage loop-closing situations. In recent\nyears, numerous researchers have proposed global registration methods to\naddress a large number of outlier correspondences. Unfortunately, the\ndegeneracy problem, which represents the phenomenon in which the number of\nestimated inliers becomes lower than three, is still potentially inevitable. To\ntackle the problem, a degeneracy-robust decoupling-based global registration\nmethod is proposed, called Quatro. In particular, our method employs\nquasi-SO(3) estimation by leveraging the Atlanta world assumption in urban\nenvironments to avoid degeneracy in rotation estimation. Thus, the minimum\ndegree of freedom (DoF) of our method is reduced from three to one. As verified\nin indoor and outdoor 3D LiDAR datasets, our proposed method yields robust\nglobal registration performance compared with other global registration\nmethods, even for distant point cloud pairs. Furthermore, the experimental\nresults confirm the applicability of our method as a coarse alignment. Our code\nis available: https://github.com/url-kaist/quatro.\n