Real-world point clouds usually suffer from incompleteness and display different poses. While current point cloud completion methods excel in reproducing complete point clouds with consistent poses as seen in the training set, their performance tends to be unsatisfactory when handling point clouds with diverse poses. We propose a network named Rotation-Invariant Completion Network (RICNet), which consists of two parts: a Dual Pipeline Completion Network (DPCNet) and an enhancing module. Firstly, DPCNet generates a coarse complete point cloud. The feature extraction module of DPCNet can extract consistent features, no matter if the input point cloud has undergone rotation or translation. Subsequently, the enhancing module refines the fine-grained details of the final generated point cloud. RICNet achieves better rotation invariance in feature extraction and incorporates structural relationships in man-made objects. To assess the performance of RICNet and existing methods on point clouds with various poses, we applied random transformations to the point clouds in the MVP dataset and conducted experiments on them. Our experiments demonstrate that RICNet exhibits superior completion performance compared to existing methods.

翻译：真实世界中的点云通常存在不完整性并展示出不同的姿态。尽管当前的点云补全方法在复现与训练集中姿态一致的完整点云方面表现出色，但在处理具有多样姿态的点云时，其性能往往不尽如人意。我们提出了一种名为旋转不变补全网络（RICNet）的模型，该网络由两部分组成：双流水线补全网络（DPCNet）和一个增强模块。首先，DPCNet生成一个粗糙的完整点云。DPCNet的特征提取模块能够提取一致的特征，无论输入点云是否经历了旋转或平移。随后，增强模块进一步优化最终生成点云的细粒度细节。RICNet在特征提取中实现了更好的旋转不变性，并融入了人造物体的结构关系。为了评估RICNet及现有方法在具有不同姿态的点云上的性能，我们对MVP数据集中的点云应用了随机变换，并在此基础上进行了实验。我们的实验表明，与现有方法相比，RICNet表现出了更优的补全性能。