Despite the recent development of deep learning-based point cloud upsampling, most MLP-based point cloud upsampling methods have limitations in that it is difficult to train the local and global structure of the point cloud at the same time. To solve this problem, we present a combined graph convolution and transformer for point cloud upsampling, denoted by PU-EdgeFormer. The proposed method constructs EdgeFormer unit that consists of graph convolution and multi-head self-attention modules. We employ graph convolution using EdgeConv, which learns the local geometry and global structure of point cloud better than existing point-to-feature method. Through in-depth experiments, we confirmed that the proposed method has better point cloud upsampling performance than the existing state-of-the-art method in both subjective and objective aspects. The code is available at https://github.com/dohoon2045/PU-EdgeFormer.

翻译：尽管基于深度学习的点云上采样技术近期取得进展，但大多数基于多层感知器的点云上采样方法存在难以同时训练点云局部与全局结构的问题。为解决该问题，我们提出一种融合图卷积与Transformer的点云上采样方法，命名为PU-EdgeFormer。该方法构建由图卷积与多头自注意力模块组成的EdgeFormer单元。我们采用基于EdgeConv的图卷积，相较于现有逐点特征方法能更有效地学习点云的局部几何与全局结构。通过深入实验，我们证实该方法在主观与客观两方面均优于现有最先进方法的点云上采样性能。代码开源地址为https://github.com/dohoon2045/PU-EdgeFormer。