As a fundamental problem in computer vision, point cloud registration aims to seek the optimal transformation for aligning a pair of point clouds. In most existing methods, the information flows are usually forward transferring, thus lacking the guidance from high-level information to low-level information. Besides, excessive high-level information may be overly redundant, and directly using it may conflict with the original low-level information. In this paper, we propose a novel Iterative Feedback Network (IFNet) for unsupervised point cloud registration, in which the representation of low-level features is efficiently enriched by rerouting subsequent high-level features. Specifically, our IFNet is built upon a series of Feedback Registration Block (FRB) modules, with each module responsible for generating the feedforward rigid transformation and feedback high-level features. These FRB modules are cascaded and recurrently unfolded over time. Further, the Feedback Transformer is designed to efficiently select relevant information from feedback high-level features, which is utilized to refine the low-level features. What's more, we incorporate a geometry-awareness descriptor to empower the network for making full use of most geometric information, which leads to more precise registration results. Extensive experiments on various benchmark datasets demonstrate the superior registration performance of our IFNet.

翻译：作为计算机视觉中的基础问题，点云配准旨在寻找最优变换以对齐一对点云。现有方法中的信息流通常为前向传递，缺乏高层次信息对低层次信息的引导。此外，过多的层次信息可能冗余过度，直接使用会与原始低层次信息产生冲突。本文提出一种用于无监督点云配准的新型迭代式反馈网络（IFNet），通过重新路由后续的高层次特征有效丰富低层次特征的表示。具体而言，IFNet基于一系列反馈配准模块（FRB）构建，每个模块负责生成前向刚体变换和反馈高维特征。这些FRB模块随时间级联并循环展开。进一步地，我们设计了反馈变换器（Feedback Transformer），从反馈高维特征中高效选择相关信息，用于优化低层次特征。此外，我们引入几何感知描述符，使网络能够充分利用几何信息，从而获得更精确的配准结果。在多个基准数据集上的大量实验表明，我们的IFNet具有卓越的配准性能。