OAAFormer:Robust and Efficient Point Cloud Registration Through Overlapping-Aware Attention in Transformer  

作　　者：Jun-Jie Gao Qiu-Jie Dong Rui-An Wang Shuang-Min Chen Shi-Qing Xin Chang-He Tu Wenping Wang 高俊杰;董秋杰;王瑞安;陈双敏;辛士庆;屠长河;王文平(School of Computer Science and Technology,Shandong University,Qingdao 266237,China;School of Information and Technology,Qingdao University of Science and Technology,Qingdao 266061,China;College of Engineering,Texas A&M University,Texas,TX 77843,U.S.A.)

机构地区：[1]School of Computer Science and Technology,Shandong University,Qingdao 266237,China [2]School of Information and Technology,Qingdao University of Science and Technology,Qingdao 266061,China [3]College of Engineering,Texas A&M University,Texas,TX 77843,U.S.A.

出　　处：《Journal of Computer Science & Technology》2024年第4期755-770,共16页计算机科学技术学报（英文版）

基　　金：supported by the National Natural Science Foundation of China under Grant Nos.62272277,U23A20312,and 62072284;the National Key Technology Research and Development Program of the Ministry of Science and Technology of China under Grant No.2022YFB3303200;the Natural Science Foundation of Shandong Province of China under Grant No.ZR2020MF036.

摘　　要：In the domain of point cloud registration,the coarse-to-fine feature matching paradigm has received significant attention due to its impressive performance.This paradigm involves a two-step process:first,the extraction of multilevel features,and subsequently,the propagation of correspondences from coarse to fine levels.However,this approach faces two notable limitations.Firstly,the use of the Dual Softmax operation may promote one-to-one correspondences between superpoints,inadvertently excluding valuable correspondences.Secondly,it is crucial to closely examine the overlapping areas between point clouds,as only correspondences within these regions decisively determine the actual transformation.Considering these issues,we propose OAAFormer to enhance correspondence quality.On the one hand,we introduce a soft matching mechanism to facilitate the propagation of potentially valuable correspondences from coarse to fine levels.On the other hand,we integrate an overlapping region detection module to minimize mismatches to the greatest extent possible.Furthermore,we introduce a region-wise attention module with linear complexity during the fine-level matching phase,designed to enhance the discriminative capabilities of the extracted features.Tests on the challenging 3DLoMatch benchmark demonstrate that our approach leads to a substantial increase of about 7%in the inlier ratio,as well as an enhancement of 2%-4%in registration recall.Finally,to accelerate the prediction process,we replace the Conventional Random Sample Consensus(RANSAC)algorithm with the selection of a limited yet representative set of high-confidence correspondences,resulting in a 100 times speedup while still maintaining comparable registration performance.

关 键 词：point cloud registration coarse-to-fine overlapping region feature matching TRANSFORMER 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]