GeoGCN: Geometric Dual-domain Graph Convolution Network for Point Cloud Denoising

2022-10-28 · Zhaowei Chen, Peng Li, Zeyong Wei, Honghua Chen, Haoran Xie, Mingqiang Wei, Fu Lee Wang

We propose GeoGCN, a novel geometric dual-domain graph convolution network for point cloud denoising (PCD). Beyond the traditional wisdom of PCD, to fully exploit the geometric information of point clouds, we define two kinds of surface normals, one is called Real Normal (RN), and the other is Virtual Normal (VN). RN preserves the local details of noisy point clouds while VN avoids the global shape shrinkage during denoising. GeoGCN is a new PCD paradigm that, 1) first regresses point positions by spatialbased GCN with the help of VNs, 2) then estimates initial RNs by performing Principal Component Analysis on the regressed points, and 3) finally regresses fine RNs by normalbased GCN. Unlike existing PCD methods, GeoGCN not only exploits two kinds of geometry expertise (i.e., RN and VN) but also benefits from training data. Experiments validate that GeoGCN outperforms SOTAs in terms of both noise-robustness and local-and-global feature preservation.

📄 PDF Abstract BibTeX arXiv:2210.15913

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising

Methods 이 논문이 사용한 방법론

GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Learning Graph Convolution Filters from Data Manifold

2018-01-01 · ICLR 2018 1 · Guokun Lai, Hanxiao Liu, Yiming Yang

Convolution Neural Network (CNN) has gained tremendous success in computer vision tasks with its outstanding ability to capture the local latent features. Recently, there has been an increasing interest in extending CNNs…

Residual Attention Graph Convolutional Network for Geometric 3D Scene Classification

2019-09-30 · Albert Mosella-Montoro, Javier Ruiz-Hidalgo

Geometric 3D scene classification is a very challenging task. Current methodologies extract the geometric information using only a depth channel provided by an RGB-D sensor. These kinds of methodologies introduce possibl…

Classification General Classification Scene Classification

Convolutional Neural Networks on Manifolds: From Graphs and Back

2022-10-01 · Zhiyang Wang, Luana Ruiz, Alejandro Ribeiro

Geometric deep learning has gained much attention in recent years due to more available data acquired from non-Euclidean domains. Some examples include point clouds for 3D models and wireless sensor networks in communica…

Point Cloud Denoising With Fine-Granularity Dynamic Graph Convolutional Networks

2024-11-21 · Wenqiang Xu, Wenrui Dai, Duoduo Xue, Ziyang Zheng 외

Due to limitations in acquisition equipment, noise perturbations often corrupt 3-D point clouds, hindering down-stream tasks such as surface reconstruction, rendering, and further processing. Existing 3-D point cloud den…

Denoising graph construction Surface Reconstruction

Graph Neural Networks on SPD Manifolds for Motor Imagery Classification: A Perspective from the Time-Frequency Analysis

2022-10-25 · Ce Ju, Cuntai Guan

The motor imagery (MI) classification has been a prominent research topic in brain-computer interfaces based on electroencephalography (EEG). Over the past few decades, the performance of MI-EEG classifiers has seen grad…

Classification EEG Electroencephalogram (EEG)Motor Imagery+1