Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks

03/28/2021
by   Siddharth Srivastava, et al.
0

We propose simple yet effective improvements in point representations and local neighborhood graph construction within the general framework of graph neural networks (GNNs) for 3D point cloud processing. As a first contribution, we propose to augment the vertex representations with important local geometric information of the points, followed by nonlinear projection using a MLP. As a second contribution, we propose to improve the graph construction for GNNs for 3D point clouds. The existing methods work with a k-nn based approach for constructing the local neighborhood graph. We argue that it might lead to reduction in coverage in case of dense sampling by sensors in some regions of the scene. The proposed methods aims to counter such problems and improve coverage in such cases. As the traditional GNNs were designed to work with general graphs, where vertices may have no geometric interpretations, we see both our proposals as augmenting the general graphs to incorporate the geometric nature of 3D point clouds. While being simple, we demonstrate with multiple challenging benchmarks, with relatively clean CAD models, as well as with real world noisy scans, that the proposed method achieves state of the art results on benchmarks for 3D classification (ModelNet40) , part segmentation (ShapeNet) and semantic segmentation (Stanford 3D Indoor Scenes Dataset). We also show that the proposed network achieves faster training convergence, i.e.  40 https://siddharthsrivastava.github.io/publication/geomgcnn/

READ FULL TEXT

page 1

page 6

research
09/20/2019

Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds

We propose a spherical kernel for efficient graph convolution of 3D poin...
research
06/05/2022

HPGNN: Using Hierarchical Graph Neural Networks for Outdoor Point Cloud Processing

Inspired by recent improvements in point cloud processing for autonomous...
research
07/30/2020

Cascaded Non-local Neural Network for Point Cloud Semantic Segmentation

In this paper, we propose a cascaded non-local neural network for point ...
research
04/03/2019

Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning

We propose a new supervized learning framework for oversegmenting 3D poi...
research
10/18/2020

Graphite: GRAPH-Induced feaTure Extraction for Point Cloud Registration

3D Point clouds are a rich source of information that enjoy growing popu...
research
11/28/2021

PAPooling: Graph-based Position Adaptive Aggregation of Local Geometry in Point Clouds

Fine-grained geometry, captured by aggregation of point features in loca...
research
09/17/2023

Performance of Graph Neural Networks for Point Cloud Applications

Graph Neural Networks (GNNs) have gained significant momentum recently d...

Please sign up or login with your details

Forgot password? Click here to reset