Local Spectral Graph Convolution for Point Set Feature Learning

Abstract

Feature learning on point clouds has shown great promise, with the introduction of effective and generalizable deep learning frameworks such as pointnet++. Thus far, however, point features have been abstracted in an independent and isolated manner, ignoring the relative layout of neighboring points as well as their features. In the present article, we propose to overcome this limitation by using spectral graph convolution on a local graph, combined with a novel graph pooling strategy. In our approach, graph convolution is carried out on a nearest neighbor graph constructed from a point's neighborhood, such that features are jointly learned. We replace the standard max pooling step with a recursive clustering and pooling strategy, devised to aggregate information from within clusters of nodes that are close to one another in their spectral coordinates, leading to richer overall feature descriptors. Through extensive experiments on diverse datasets, we show a consistent demonstrable advantage for the tasks of both point set classification and segmentation.

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• 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
• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
• Multi-view Convolutional Neural Networks for 3D Shape Recognition

Cited by in corpus (17)

• Graph-based Spatial-temporal Feature Learning for Neuromorphic Vision Sensing
• PointCNN: Convolution On $\mathcal{X}$-Transformed Points
• Graph Convolutional Networks for Graphs Containing Missing Features
• Interpolated Convolutional Networks for 3D Point Cloud Understanding
• Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topology
• Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects
• Geometric Back-projection Network for Point Cloud Classification
• Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN
• Data-Free Point Cloud Network for 3D Face Recognition
• Graph-Based Object Classification for Neuromorphic Vision Sensing
• Geometry Sharing Network for 3D Point Cloud Classification and Segmentation
• NPTC-net: Narrow-Band Parallel Transport Convolutional Neural Network on Point Clouds
• Graph Attribute Aggregation Network with Progressive Margin Folding
• Spatial Transformer Point Convolution
• Learnable Pooling in Graph Convolution Networks for Brain Surface Analysis
• Zero-shot Learning of 3D Point Cloud Objects
• MARNet: Multi-Abstraction Refinement Network for 3D Point Cloud Analysis