基于深度位置感知Transformer的低重叠点云配准  

Low Overlap Point Cloud Registration Method Based on Deep Position-aware Transformer

作　　者：孔煜 熊风光[1,2,3] 张志强 申超凡 胡明月 KONG Yu;XIONG Fengguang;ZHANG Zhiqiang;SHEN Chaofan;HU Mingyue(School of Computer Science and Technology,North University of China,Taiyuan 030051,China;Shanxi Provincial Key Laboratory of Machine Vision and Virtual Reality,Taiyuan 030051,China;Shanxi Province’s Vision Information Processing and Intelligent Robot Engineering Research Center,Taiyuan 030051,China)

机构地区：[1]中北大学计算机科学与技术学院,太原030051 [2]机器视觉与虚拟现实山西省重点实验室,太原030051 [3]山西省视觉信息处理及智能机器人工程研究中心,太原030051

出　　处：《计算机科学》2025年第5期199-211,共13页Computer Science

基　　金：国家自然科学基金(62272426);山西省自然科学基金(202203021212138);山西省科技重大专项计划“揭榜挂帅”项目(202201150401021)。

摘　　要：针对特征提取阶段忽视局部几何嵌入的融合,特征交互阶段低重叠点云对之间的位置感知信息呈现弱相关性导致难以提取更富有表现力的特征,以及对应生成阶段出现部分错误对应导致求解的变换矩阵存在偏差等问题,提出了一种基于深度位置感知Transformer(DeepPAT)的三维点云低重叠配准方法。首先,设计了融合局部几何信息的局部特征提取网络,用于提取点云多层次特征;然后,设计了基于深度位置感知的Transformer(PAT)模块,通过学习点云自身和跨帧的几何和深度空间位置信息,提取低重叠率的源点云和目标点云的相关特征和重叠信息,以便进行低重叠特征匹配;最后,设计了由特征相似性项调节的极大团算法来减轻长度一致性所带来的空间模糊性,从而过滤离群点。其可作为一种即插即用的估计模块代替RANSAC等传统鲁棒估计器。在室内3DMatch数据集和合成ModelNet数据集上进行评估,实验结果表明:在测试ModelNet数据集的旋转和平移均方根误差方面,DeepPAT分别将误差降低至3.994和0.005;在测试3DMatch和3DLoMatch基准的配准召回率方面,DeepPAT分别比现有方法高出至少4.3%和3.6%。In response to the issues such as neglecting the fusion of local geometric embeddings in the feature extraction stage,weak correlation in position-aware information between low overlap point cloud pairs in the feature interaction stage,making it difficult to extract more expressive features and deviation in the transformation solved due to some outlier correspondence in the correspondence generation stage,in this paper,a 3D point cloud low overlap registration method based on deep position-aware Transformer(DeepPAT)is proposed,which follows the local to global matching mechanism.A local feature extraction network based on local geometry information is proposed to extract multi-level features from point cloud.Then,a deep position-aware Transformer(DPAT)module is designed to extract the relevant features and overlap information between low overlap point cloud pairs by learning the geometry and spatial position information of the point cloud itself and across frames,so as to carry out low overlap point cloud matching.Finally,a maximal cliques algorithm adjusted by the feature similarity is designed to reduce the position ambiguity caused by the length consistency and eliminate the outlier correspondences.It can be used as a plug-and-play robust estimator to replace traditional robust estimators such as RANSAC and is fully implemented by Pytorch.Evaluating on the synthetic ModelNet dataset and indoor 3DMatch dataset,the experimental results show that DeepPAT reduces the rotation and translation root mean square error to 3.994 and 0.005 on ModelNet datasets,respectively,and DeepPAT outperformed existing methods by at least 4.3 percentage points and 3.6 percentage points in term of registration recall on 3DMatch and 3DLoMatch benchmarks,respectively.

关 键 词：低重叠率 极大团 局部特征提取 深度位置感知 局部到全局匹配 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]