IEEE Trans Pattern Anal Mach Intell. 2023 May;45(5):6183-6195. doi: 10.1109/TPAMI.2022.3204713. Epub 2023 Apr 3.
3D point cloud registration is a fundamental problem in computer vision and robotics. Recently, learning-based point cloud registration methods have made great progress. However, these methods are sensitive to outliers, which lead to more incorrect correspondences. In this paper, we propose a novel deep graph matching-based framework for point cloud registration. Specifically, we first transform point clouds into graphs and extract deep features for each point. Then, we develop a module based on deep graph matching to calculate a soft correspondence matrix. By using graph matching, not only the local geometry of each point but also its structure and topology in a larger range are considered in establishing correspondences, so that more correct correspondences are found. We train the network with a loss directly defined on the correspondences, and in the test stage the soft correspondences are transformed into hard one-to-one correspondences so that registration can be performed by a correspondence-based solver. Furthermore, we introduce a transformer-based method to generate edges for graph construction, which further improves the quality of the correspondences. Extensive experiments on object-level and scene-level benchmark datasets show that the proposed method achieves state-of-the-art performance.
三维点云配准是计算机视觉和机器人学中的一个基本问题。最近，基于学习的点云配准方法取得了很大的进展。然而，这些方法对点云数据中的离群点很敏感，容易导致更多错误的对应关系。在本文中，我们提出了一种新颖的基于深度图匹配的点云配准框架。具体来说，我们首先将点云转换为图，并为每个点提取深度特征。然后，我们开发了一个基于深度图匹配的模块来计算软对应矩阵。通过使用图匹配，不仅可以考虑每个点的局部几何形状，还可以考虑更大范围内的结构和拓扑关系，从而找到更多正确的对应关系。我们使用直接定义在对应关系上的损失来训练网络，在测试阶段，软对应关系被转换为硬一一对应关系，以便通过基于对应关系的求解器进行配准。此外，我们引入了一种基于 Transformer 的方法来生成图的边，这进一步提高了对应关系的质量。在物体级和场景级基准数据集上的广泛实验表明，所提出的方法取得了最先进的性能。
