Deep learning based point cloud registration: an overview

Point cloud registration aims at finding a rigid transformation to align one point cloud to another one. It is a fundamental problem in computer vision and robotics, which has been widely used in various applications, such as 3D reconstruction, SLAM (simultaneous localization and mapping), and autonomous driving. Over the last decades, many researchers have devoted themselves to tackle this challenging problem. Recently, the success of deep learning in high-level vision tasks has been extended to different geometric vision tasks. Various kinds of deep learning based point cloud registration methods have been proposed to exploit different aspects of the problem. However, a comprehensive overview of these approaches is still missing. To this end, in this paper, we summarize recent progress and present a comprehensive overview for deep learning based point cloud registration. We classify the popular approaches into different categories such as, correspondences-based or correspondences-free, effective modules: feature extractor, matching, outlier rejection, and motion estimation. Furthermore, we discuss the merits and demerits in detail. We provide a systematic and compact framework towards currently proposed methods and discuss future research directions.