The effectiveness of learning-based point cloud upsampling pipelines heavily relies on the upsampling modules and feature extractors used therein. We propose three novel point upsampling modules: Multi-branch GCN, Clone GCN, and NodeShuffle. Our modules use Graph Convolutional Networks (GCNs) to better encode local point information from the point neighborhood. These upsampling modules are versatile and can be incorporated into any point cloud upsampling pipeline. Extensive experiments show how these modules consistently improve state-of-the-art upsampling methods. We also propose a new multi-scale point feature extractor, called Inception DenseGCN. By aggregating features at multiple scales, this feature extractor enables further performance gain in the final upsampled point clouds. We combine Inception DenseGCN with one of our upsampling modules (NodeShuffle) into a new point upsampling pipeline: PU-GCN. We show qualitatively and quantitatively the significant advantages of PU-GCN over the state-of-the-art. The website and source code of this work are available at https://sites.google.com/kaust.edu.sa/pugcn and https://github.com/guochengqian/PU-GCN respectively.

中文翻译：

---

PU-GCN：使用图卷积网络的点云上采样

基于学习的点云上采样管道的有效性在很大程度上依赖于其中使用的上采样模块和特征提取器。我们提出了三个新颖的点上采样模块：多分支 GCN、克隆 GCN 和 NodeShuffle。我们的模块使用图卷积网络 (GCN) 来更好地编码来自点邻域的局部点信息。这些上采样模块用途广泛，可以合并到任何点云上采样管道中。大量实验表明这些模块如何持续改进最先进的上采样方法。我们还提出了一种新的多尺度点特征提取器，称为 Inception DenseGCN。通过在多个尺度上聚合特征，该特征提取器可以进一步提高最终上采样点云的性能。我们将 Inception DenseGCN 与我们的一个上采样模块（NodeShuffle）结合成一个新的点上采样管道：PU-GCN。我们定性和定量地展示了 PU-GCN 相对于最先进技术的显着优势。本作品的网址和源代码分别位于 https://sites.google.com/kaust.edu.sa/pugcn 和 https://github.com/guochengqian/PU-GCN。