Lv Chenlei, Lin Weisi, Zhao Baoquan
IEEE Trans Image Process. 2023;32:1681-1693. doi: 10.1109/TIP.2023.3251021. Epub 2023 Mar 9.
Point cloud registration is a popular topic that has been widely used in 3D model reconstruction, location, and retrieval. In this paper, we propose a new registration method, KSS-ICP, to address the rigid registration task in Kendall shape space (KSS) with Iterative Closest Point (ICP). The KSS is a quotient space that removes influences of translations, scales, and rotations for shape feature-based analysis. Such influences can be concluded as the similarity transformations that do not change the shape feature. The point cloud representation in KSS is invariant to similarity transformations. We utilize such property to design the KSS-ICP for point cloud registration. To tackle the difficulty to achieve the KSS representation in general, the proposed KSS-ICP formulates a practical solution that does not require complex feature analysis, data training, and optimization. With a simple implementation, KSS-ICP achieves more accurate registration from point clouds. It is robust to similarity transformation, non-uniform density, noise, and defective parts. Experiments show that KSS-ICP has better performance than the state-of-the-art. Code (vvvwo/KSS-ICP) and executable files (vvvwo/KSS-ICP/tree/master/EXE) are made public.
点云配准是一个热门话题，已广泛应用于三维模型重建、定位和检索中。在本文中，我们提出了一种新的配准方法——KSS-ICP，用于在肯德尔形状空间（KSS）中结合迭代最近点（ICP）算法解决刚体配准任务。KSS是一个商空间，它消除了平移、缩放和旋转对基于形状特征分析的影响。这些影响可归结为不改变形状特征的相似变换。KSS中的点云表示对相似变换具有不变性。我们利用这一特性设计了用于点云配准的KSS-ICP算法。为了解决一般情况下难以实现KSS表示的问题，所提出的KSS-ICP算法制定了一种实用的解决方案，该方案不需要复杂的特征分析、数据训练和优化。通过简单的实现，KSS-ICP算法能从点云中实现更精确的配准。它对相似变换、非均匀密度、噪声和缺陷部分具有鲁棒性。实验表明，KSS-ICP算法的性能优于现有技术。代码（vvvwo/KSS-ICP）和可执行文件（vvvwo/KSS-ICP/tree/master/EXE）已公开。
