PointWavelet: Learning in Spectral Domain for 3D Point Cloud Analysis
This addresses the challenge of spectral domain learning for 3D point clouds, which is incremental as it builds on existing deep learning methods.
The paper tackles the problem of 3D point cloud analysis by exploring local structures in the spectral domain, introducing PointWavelet with a learnable graph wavelet transform, and achieves effective results on classification and segmentation across four datasets.
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.