Point Cloud Denoising Using Normal Vector-Based Graph Wavelet Shrinkage
Ryosuke Watanabe, Keisuke Nonaka, Haruhisa Kato, Eduardo Pavez, Tatsuya Kobayashi, Antonio Ortega
Abstract
Many applications that use point clouds, such as 3D immersive telepresence, suffer from geometric quality degradation. This noise may be caused by measurement errors of the capturing device or by the point cloud estimation method. In this paper, we propose a novel graph-based point cloud denoising approach using the spectral graph wavelet transform (SGWT) and graph wavelet shrinkage. Unlike conventional SGWT-based denoising methods, the proposed wavelet shrinkage thresholds are determined based on the normal vector at each point and are thus based on the local geometric structure of the point cloud. This approach avoids excessive wavelet shrinkage, which can lead to the loss of complex geometric structure. Experimental results show that the proposed method achieves the best accuracy as compared with recent deep-learning-based and graph-based state-of-the-art denoising methods.
BibTeX
@inproceedings{icassp2022_pointclouddenois,
title = {Point Cloud Denoising Using Normal Vector-Based Graph Wavelet Shrinkage},
author = {Ryosuke Watanabe and Keisuke Nonaka and Haruhisa Kato and Eduardo Pavez and Tatsuya Kobayashi and Antonio Ortega},
booktitle = {ICASSP 2022},
year = {2022}
}