Point cloud shape completion is a challenging problem in 3D vision and robotics. Existing learning-based frameworks leverage encoder-decoder architectures to recover the complete shape from a highly encoded global feature vector. Though the global feature can approximately represent the overall shape of 3D objects, it would lead to the loss of shape details during the completion process. In this work, instead of using a global feature to recover the whole complete surface, we explore the functionality of multi-level features and aggregate different features to represent the known part and the missing part separately. We propose two different feature aggregation strategies, named global \& local feature aggregation(GLFA) and residual feature aggregation(RFA), to express the two kinds of features and reconstruct coordinates from their combination. In addition, we also design a refinement component to prevent the generated point cloud from non-uniform distribution and outliers. Extensive experiments have been conducted on the ShapeNet dataset. Qualitative and quantitative evaluations demonstrate that our proposed network outperforms current state-of-the art methods especially on detail preservation.

中文翻译：

---

通过分离的特征聚合细节保留点云完成

点云形状补全是 3D 视觉和机器人技术中的一个具有挑战性的问题。现有的基于学习的框架利用编码器-解码器架构从高度编码的全局特征向量中恢复完整的形状。虽然全局特征可以近似表示3D物体的整体形状，但在完成过程中会导致形状细节的丢失。在这项工作中，我们不是使用全局特征来恢复整个完整表面，而是探索多级特征的功能并聚合不同的特征来分别表示已知部分和缺失部分。我们提出了两种不同的特征聚合策略，命名为全局\&局部特征聚合（GLFA）和残差特征聚合（RFA），表达两种特征，并从它们的组合中重建坐标。此外，我们还设计了一个细化组件，以防止生成的点云分布不均和异常值。已经在 ShapeNet 数据集上进行了大量实验。定性和定量评估表明，我们提出的网络优于当前最先进的方法，尤其是在细节保留方面。