Point cloud completion aims to infer a complete shape from its partial observation. Many approaches utilize a pure encoderdecoder paradigm in which complete shape can be directly predicted by shape priors learned from partial scans, however, these methods suffer from the loss of details inevitably due to the feature abstraction issues. In this paper, we propose a novel framework,termed SPAC-Net, that aims to rethink the completion task under the guidance of a new structural prior, we call it interface. Specifically, our method first investigates Marginal Detector (MAD) module to localize the interface, defined as the intersection between the known observation and the missing parts. Based on the interface, our method predicts the coarse shape by learning the displacement from the points in interface move to their corresponding position in missing parts. Furthermore, we devise an additional Structure Supplement(SSP) module before the upsampling stage to enhance the structural details of the coarse shape, enabling the upsampling module to focus more on the upsampling task. Extensive experiments have been conducted on several challenging benchmarks, and the results demonstrate that our method outperforms existing state-of-the-art approaches.

翻译：点云补全旨在从部分观测中推断出完整的形状。许多方法采用纯编码器-解码器范式，其中完整形状可以通过从局部扫描中学习到的形状先验直接预测。然而，由于特征抽象问题，这些方法不可避免地会损失细节。在本文中，我们提出了一种新颖的框架，称为SPAC-Net，旨在一种我们称之为“界面”的新结构先验的指导下重新思考补全任务。具体而言，我们的方法首先通过边缘检测器模块定位界面，该界面被定义为已知观测与缺失部分之间的交集。基于此界面，我们的方法通过学习界面中的点移动到缺失部分中对应位置的位移来预测粗略形状。此外，我们在上采样阶段之前设计了一个额外的结构补充模块，以增强粗略形状的结构细节，从而使上采样模块能更专注于上采样任务。我们在多个具有挑战性的基准数据集上进行了广泛的实验，结果表明我们的方法优于现有的最先进方法。