D3Former：通过显著性引导Transformer联合学习可重复稠密检测器与特征增强描述符
D3Former: Jointly Learning Repeatable Dense Detectors and Feature-enhanced Descriptors via Saliency-guided Transformer
AI总结：
本文提出D3Former，一种显著性引导Transformer，联合学习可重复稠密检测器与特征增强描述符，在室内外基准上优于现有方法，如3DLoMatch上配准召回率达76.5%。
摘要：
建立准确且具有代表性的匹配是解决点云配准问题的关键步骤。一种常用的方法涉及检测具有显著几何特征的关键点，随后将这些关键点从点云的一帧映射到另一帧。然而，此类方法受限于采样关键点的可重复性。在本文中，我们引入了一种显著性引导的Transformer，称为D3Former，它涉及可重复稠密检测器与特征增强描述符的联合学习。该模型包含一个特征增强描述符学习（FEDL）模块和一个可重复关键点检测器学习（RKDL）模块。FEDL模块利用区域注意力机制来增强特征独特性，而RKDL模块专注于检测可重复关键点以增强匹配能力。在具有挑战性的室内和室外基准上的大量实验结果表明，我们提出的方法始终优于最先进的点云匹配方法。值得注意的是，即使在低重叠率下，在3DLoMatch上的测试也表明，我们的方法始终优于最近发布的方法，如RoReg和RoITr。例如，当提取的关键点数量减少到250时，RoReg、RoITr和我们的方法的配准召回分数分别为64.3%、73.6%和76.5%。
英文摘要：
Establishing accurate and representative matches is a crucial step in addressing the point cloud registration problem. A commonly employed approach involves detecting keypoints with salient geometric features and subsequently mapping these keypoints from one frame of the point cloud to another. However, methods within this category are hampered by the repeatability of the sampled keypoints. In this paper, we introduce a saliency-guided trans\textbf{former}, referred to as \textit{D3Former}, which entails the joint learning of repeatable \textbf{D}ense \textbf{D}etectors and feature-enhanced \textbf{D}escriptors. The model comprises a Feature Enhancement Descriptor Learning (FEDL) module and a Repetitive Keypoints Detector Learning (RKDL) module. The FEDL module utilizes a region attention mechanism to enhance feature distinctiveness, while the RKDL module focuses on detecting repeatable keypoints to enhance matching capabilities. Extensive experimental results on challenging indoor and outdoor benchmarks demonstrate that our proposed method consistently outperforms state-of-the-art point cloud matching methods. Notably, tests on 3DLoMatch, even with a low overlap ratio, show that our method consistently outperforms recently published approaches such as RoReg and RoITr. For instance, with the number of extracted keypoints reduced to 250, the registration recall scores for RoReg, RoITr, and our method are 64.3\%, 73.6\%, and 76.5\%, respectively.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
