信息与控制2025，Vol.54Issue(3)：428-441,14.DOI:10.13976/j.cnki.xk.2024.0751
基于对应关系学习与空间一致性的点云配准
Point Cloud Registration via Correspondence Learning and Spatial Consistency
摘要
Abstract
We introduce a novel method for point cloud registration that effectively estimates the transformation between two partially overlapping point clouds.By adopting advanced correspon-dence learning techniques and emphasizing the spatial consistency of superpoints,the accuracy of coarse matching is significantly enhanced.Additionally,the concept of saliency scores is intro-duced and innovatively applied to extracting correspondence relationships,thereby improving the accuracy of transformation estimation.Moreover,a series of novel loss function combinations,in-cluding coarse matching loss,fine matching loss,and saliency score loss,have been designed to optimize model performance and enhance registration accuracy.Experimental results demonstrate the excellent performance of this method in point cloud registration tasks,effectively improving the inlier ratio,feature matching recall rate,and registration recall rate.The method exhibits exceptional robustness in various noise environments and shows advantages under different overlap conditions.Ablation studies further confirm the critical role of geometric consistency and saliency scores in en-hancing registration precision.关键词
点云处理/点云配准/对应关系学习/空间一致性Key words
point cloud processing/point cloud registration/correspondence learning/spatial consistency分类
信息技术与安全科学引用本文复制引用
李营浩,夏仁波,赵吉宾,易俊兰,邱太文..基于对应关系学习与空间一致性的点云配准[J].信息与控制,2025,54(3):428-441,14.基金项目
国家自然科学基金项目(52075532,91948203) （52075532,91948203）
