PointWavelet: Learning in Spectral Domain for 3D Point Cloud Analysis

TL;DR

PointWavelet introduces a spectral domain approach for 3D point cloud analysis using a learnable graph wavelet transform, enhancing local structure learning and accelerating training.

Contribution

It proposes a novel learnable graph wavelet transform for spectral domain analysis, improving efficiency and effectiveness in 3D point cloud tasks.

Findings

Effective in point cloud classification and segmentation

Outperforms existing methods on multiple datasets

Accelerates training through learnable spectral transforms

Abstract

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.