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.
Learning to Tessellate: Point Cloud Generation via Recursive Spectral Partitioning
South China University of Technology（华南理工大学）；University of Chinese Academy of Sciences（中国科学院大学）；City University of Hong Kong（香港城市大学）；Singapore Management University（新加坡管理大学）
PWAVEP: Purifying Imperceptible Adversarial Perturbations in 3D Point Clouds via Spectral Graph Wavelets
Software College, Northeastern University（东北大学软件学院）；Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究所）；Software College, Shenyang University of Technology（沈阳理工大学软件学院）
STS-Mixer: Spatio-Temporal-Spectral Mixer for 4D Point Cloud Video Understanding
Nanyang Technological University（南洋理工大学）；Alibaba Group（阿里巴巴集团）；Zhejiang University of Technology（浙江工业大学）；University of Chinese Academy of Sciences（中国科学院大学）
SRENet: Spectral Re-Entry Network for Point Cloud Action Recognition
School of Software Engineering, South China University of Technology（南方科技大学软件工程学院）；School of Automation Science and Engineering, South China University of Technology（南方科技大学自动化科学与工程学院）；School of Computer Science, University of Sydney（悉尼大学计算机科学学院）；School of Science, Edith Cowan University（爱丁堡牛津大学科学学院）
Fraunhofer-Institut für Techno- und Wirtschaftsmathematik（弗劳恩霍夫技术与经济数学研究所）；Universität Kaiserslautern（凯泽斯劳滕大学）；Hochschule Darmstadt（达姆施塔特应用科学大学）；Deutsche Institute für Textil- und Faserforschung Denkendorf（德国登肯多夫纺织与纤维研究中心）
CloudBreaker: Breaking the Cloud Covers of Sentinel-2 Images using Multi-Stage Trained Conditional Flow Matching on Sentinel-1
Computer Science and Engineering（计算机科学与工程）；Bangladesh University of Engineering and Technology（孟加拉工程与技术大学）；Institute of Water and Flood Management（水与洪水管理研究所）
