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

05/31/2021
by   Siyu Zhang, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/31/2021

Heterogeneous Graph Neural Network with Multi-view Representation Learning

Graph neural networks for heterogeneous graph embedding is to project no...
research
12/25/2019

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

In this paper, we present an InSphereNet method for the problem of 3D ob...
research
10/02/2018

Ancient Coin Classification Using Graph Transduction Games

Recognizing the type of an ancient coin requires theoretical expertise a...
research
03/18/2021

Concentric Spherical GNN for 3D Representation Learning

Learning 3D representations that generalize well to arbitrarily oriented...
research
09/17/2020

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

A robust and accurate 3D detection system is an integral part of autonom...
research
08/23/2022

Object Detection in Aerial Images with Uncertainty-Aware Graph Network

In this work, we propose a novel uncertainty-aware object detection fram...
research
11/17/2022

Do graph neural networks learn traditional jet substructure?

At the CERN LHC, the task of jet tagging, whose goal is to infer the ori...

Please sign up or login with your details

Forgot password? Click here to reset