Point Cloud Registration (PCR) estimates the relative rigid transformation between two point clouds of the same scene. Despite significant progress with learning-based approaches, existing methods still face challenges when the overlapping region between the two point clouds is small. In this paper, we propose an adaptive multi-step refinement network that refines the registration quality at each step by leveraging the information from the preceding step. To achieve this, we introduce a training procedure and a refinement network. Firstly, to adapt the network to the current step, we utilize a generalized one-way attention mechanism, which prioritizes the last step's estimated overlapping region, and we condition the network on step indices. Secondly, instead of training the network to map either random transformations or a fixed pre-trained model's estimations to the ground truth, we train it on transformations with varying registration qualities, ranging from accurate to inaccurate, thereby enhancing the network's adaptiveness and robustness. Despite its conceptual simplicity, our method achieves state-of-the-art performance on both the 3DMatch/3DLoMatch and KITTI benchmarks. Notably, on 3DLoMatch, our method reaches 80.4% recall rate, with an absolute improvement of 1.2%.

翻译：点云配准（PCR）旨在估计同一场景下两个点云之间的相对刚性变换。尽管基于学习的方法已取得显著进展，但现有方法在两个点云之间重叠区域较小时仍面临挑战。本文提出一种自适应多步优化网络，该网络通过利用前一步的信息，在每一步优化配准质量。为实现这一目标，我们引入了一种训练流程和一个优化网络。首先，为使网络适应当前步骤，我们采用了一种广义单向注意力机制，该机制优先关注上一步估计的重叠区域，并将步骤索引作为网络的条件输入。其次，我们并非训练网络将随机变换或固定预训练模型的估计映射到真实值，而是在具有不同配准质量（从精确到不精确）的变换上进行训练，从而增强网络的适应性和鲁棒性。尽管概念简洁，我们的方法在3DMatch/3DLoMatch和KITTI基准测试中均达到了最先进的性能。值得注意的是，在3DLoMatch数据集上，我们的方法实现了80.4%的召回率，绝对提升了1.2%。