SN-Graph: a Minimalist 3D Object Representation for Classification

by   Siyu Zhang, et al.

Using deep learning techniques to process 3D objects has achieved many successes. However, few methods focus on the representation of 3D objects, which could be more effective for specific tasks than traditional representations, such as point clouds, voxels, and multi-view images. In this paper, we propose a Sphere Node Graph (SN-Graph) to represent 3D objects. Specifically, we extract a certain number of internal spheres (as nodes) from the signed distance field (SDF), and then establish connections (as edges) among the sphere nodes to construct a graph, which is seamlessly suitable for 3D analysis using graph neural network (GNN). Experiments conducted on the ModelNet40 dataset show that when there are fewer nodes in the graph or the tested objects are rotated arbitrarily, the classification accuracy of SN-Graph is significantly higher than the state-of-the-art methods.



There are no comments yet.


page 1

page 2

page 3

page 4


Heterogeneous Graph Neural Network with Multi-view Representation Learning

Graph neural networks for heterogeneous graph embedding is to project no...

InSphereNet: a Concise Representation and Classification Method for 3D Object

In this paper, we present an InSphereNet method for the problem of 3D ob...

Ancient Coin Classification Using Graph Transduction Games

Recognizing the type of an ancient coin requires theoretical expertise a...

Concentric Spherical GNN for 3D Representation Learning

Learning 3D representations that generalize well to arbitrarily oriented...

Dynamic Edge Weights in Graph Neural Networks for 3D Object Detection

A robust and accurate 3D detection system is an integral part of autonom...

Optimal Transport Graph Neural Networks

Current graph neural network (GNN) architectures naively average or sum ...

High-fidelity 3D Model Compression based on Key Spheres

In recent years, neural signed distance function (SDF) has become one of...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.