Graph Signal Processing for Geometric Data and Beyond: Theory and Applications
arXiv:2008.01918
Abstract
Geometric data acquired from real-world scenes, e.g., 2D depth images, 3D point clouds, and 4D dynamic point clouds, have found a wide range of applications including immersive telepresence, autonomous driving, surveillance, etc. Due to irregular sampling patterns of most geometric data, traditional image/video processing methodologies are limited, while Graph Signal Processing (GSP) -- a fast-developing field in the signal processing community -- enables processing signals that reside on irregular domains and plays a critical role in numerous applications of geometric data from low-level processing to high-level analysis. To further advance the research in this field, we provide the first timely and comprehensive overview of GSP methodologies for geometric data in a unified manner by bridging the connections between geometric data and graphs, among the various geometric data modalities, and with spectral/nodal graph filtering techniques. We also discuss the recently developed Graph Neural Networks (GNNs) and interpret the operation of these networks from the perspective of GSP. We conclude with a brief discussion of open problems and challenges.
arXiv commentAccepted at IEEE TMM
References in corpus (28)
- Semi-Supervised Classification with Graph Convolutional Networks
- The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
- Geometric deep learning: going beyond Euclidean data
- Discrete Signal Processing on Graphs
- Deep Convolutional Networks on Graph-Structured Data
- Simplifying Graph Convolutional Networks
- Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
- ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes
- Learning graphs from data: A signal representation perspective
- Connecting the Dots: Identifying Network Structure via Graph Signal Processing
- Graph Laplacian Regularization for Image Denoising: Analysis in the Continuous Domain
- Graph signal processing for machine learning: A review and new perspectives
- Fast Resampling of 3D Point Clouds via Graphs
- Learning Discrete Structures for Graph Neural Networks
- Deep Graph-Convolutional Image Denoising
- Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features
- Feature Graph Learning for 3D Point Cloud Denoising
- Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud
- An Analysis of the Convergence of Graph Laplacians
- Irregularity-Aware Graph Fourier Transforms
- Approximate fast graph Fourier transforms via multi-layer sparse approximations
- Spectral Projector-Based Graph Fourier Transforms
- Laplacian Regularized Few-Shot Learning
- Fast Graph Fourier Transforms Based on Graph Symmetry and Bipartition
- 3D Point Cloud Processing and Learning for Autonomous Driving
- Chebyshev and Conjugate Gradient Filters for Graph Image Denoising
- Understanding Graph Neural Networks from Graph Signal Denoising Perspectives
- Graph Signal Processing -- Part III: Machine Learning on Graphs, from Graph Topology to Applications