With recent success of deep learning in 2D visual recognition, deep learning-based 3D point cloud analysis has received increasing attention from the community, especially due to the rapid development of autonomous driving technologies. However, most existing methods directly learn point features in the spatial domain, leaving the local structures in the spectral domain poorly investigated. In this paper, we introduce a new method, PointWavelet, to explore local graphs in the spectral domain via a learnable graph wavelet transform. Specifically, we first introduce the graph wavelet transform to form multi-scale spectral graph convolution to learn effective local structural representations. To avoid the time-consuming spectral decomposition, we then devise a learnable graph wavelet transform, which significantly accelerates the overall training process. Extensive experiments on four popular point cloud datasets, ModelNet40, ScanObjectNN, ShapeNet-Part, and S3DIS, demonstrate the effectiveness of the proposed method on point cloud classification and segmentation.

翻译：随着深度学习在二维视觉识别领域取得近期成功，基于深度学习的三维点云分析因自动驾驶技术的快速发展而日益受到学界关注。然而，现有方法大多在空间域直接学习点特征，导致谱域中的局部结构未得到充分研究。本文提出了一种新方法PointWavelet，通过可学习的图小波变换在谱域中探索局部图结构。具体而言，我们首先引入图小波变换构造多尺度谱图卷积，以学习有效的局部结构表示。为避免耗时谱分解，我们进一步设计了可学习图小波变换，显著加速了整体训练过程。在ModelNet40、ScanObjectNN、ShapeNet-Part和S3DIS四个主流点云数据集上的大量实验表明，该方法在点云分类与分割任务中具有有效性。