Point cloud registration is a fundamental task for estimating rigid transformations between point clouds. Previous studies have used geometric information for extracting features, matching and estimating transformation. Recently, owing to the advancement of RGB-D sensors, researchers have attempted to utilize visual information to improve registration performance. However, these studies focused on extracting distinctive features by deep feature fusion, which cannot effectively solve the negative effects of each feature's weakness, and cannot sufficiently leverage the valid information. In this paper, we propose a new feature combination framework, which applies a looser but more effective fusion and can achieve better performance. An explicit filter based on transformation consistency is designed for the combination framework, which can overcome each feature's weakness. And an adaptive threshold determined by the error distribution is proposed to extract more valid information from the two types of features. Owing to the distinctive design, our proposed framework can estimate more accurate correspondences and is applicable to both hand-crafted and learning-based feature descriptors. Experiments on ScanNet show that our method achieves a state-of-the-art performance and the rotation accuracy of 99.1%.

翻译：点云注册是估计点云之间刚性变换的基础任务。以往研究利用几何信息进行特征提取、匹配和变换估计。近年来，随着RGB-D传感器的发展，研究者尝试利用视觉信息提升注册性能。然而，这些研究侧重于通过深度特征融合提取独特特征，无法有效解决各特征缺陷带来的负面影响，也无法充分利用有效信息。本文提出一种新的特征组合框架，采用更松散但更有效的融合方式，能够实现更优性能。该组合框架设计了基于变换一致性的显式滤波器，可克服各特征缺陷；并提出了由误差分布决定的自适应阈值，以从两类特征中提取更多有效信息。凭借该独特设计，所提框架能够估计更精确的对应关系，且适用于手工设计及基于学习的特征描述子。在ScanNet上的实验表明，本方法实现了最先进的性能，旋转精度达到99.1%。