Khazari Ahmed El, Que Yue, Sung Thai Leang, Lee Hyo Jong
Division of Computer Science and Engineering, Jeonbuk National University, Jeonju 54896, Korea.
Center for Advanced Image and Information Technology, Jeonbuk National University, Jeonju 54896, Korea.
Sensors (Basel). 2020 Jul 20;20(14):4032. doi: 10.3390/s20144032.
Point cloud registration is a key problem in computer vision applications and involves finding a rigid transform from a point cloud into another such that they align together. The iterative closest point (ICP) method is a simple and effective solution that converges to a local optimum. However, despite the fact that point cloud registration or alignment is addressed in learning-based methods, such as PointNetLK, they do not offer good generalizability for point clouds. In this stud, we proposed a learning-based approach that addressed existing problems, such as finding local optima for ICP and achieving minimum generalizability. The proposed model consisted of three main parts: an encoding network, an auxiliary module that weighed the contribution of each input point cloud, and feature alignment to achieve the final transform. The proposed architecture offered greater generalization among the categories. Experiments were performed on ModelNet40 with different configurations and the results indicated that the proposed approach significantly outperformed the state-of-the-art point cloud alignment methods.
点云配准是计算机视觉应用中的一个关键问题，涉及找到一个从一个点云到另一个点云的刚性变换，以使它们对齐。迭代最近点（ICP）方法是一种简单有效的解决方案，它收敛到局部最优。然而，尽管基于学习的方法（如PointNetLK）解决了点云配准或对齐问题，但它们对点云的泛化能力不佳。在本研究中，我们提出了一种基于学习的方法，解决了诸如为ICP找到局部最优以及实现最小泛化等现有问题。所提出的模型由三个主要部分组成：一个编码网络、一个权衡每个输入点云贡献的辅助模块以及用于实现最终变换的特征对齐。所提出的架构在不同类别之间具有更强的泛化能力。在具有不同配置的ModelNet40上进行了实验，结果表明所提出的方法显著优于当前最先进的点云对齐方法。
