Robust Sim2Real 3D Object Classification Using Graph Representations and a Deep Center Voting Scheme

Weibel, JB; Patten, T; Vincze, M

Robust Sim2Real 3D Object Classification Using Graph Representations and a Deep Center Voting Scheme

Weibel, JB Patten, T

Vincze, M

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE Robotics and Automation Letters, 2022, 7, (3), pp. 8028-8035
Issue Date:: 2022-07-01

Closed Access

	Filename	Description	Size
	Robust_Sim2Real_3D_Object_Classification_Using_Graph_Representations_and_a_Deep_Center_Voting_Scheme.pdf		2.19 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Weibel, JB
dc.contributor.author	Patten, T https://orcid.org/0000-0003-1139-9451
dc.contributor.author	Vincze, M
dc.date.accessioned	2023-03-17T05:33:06Z
dc.date.available	2023-03-17T05:33:06Z
dc.date.issued	2022-07-01
dc.identifier.citation	IEEE Robotics and Automation Letters, 2022, 7, (3), pp. 8028-8035
dc.identifier.issn	2377-3766
dc.identifier.issn	2377-3766
dc.identifier.uri	http://hdl.handle.net/10453/167483
dc.description.abstract	While object semantic understanding is essential for service robotic tasks, 3D object classification is still an open problem. Learning from artificial 3D models alleviates the cost of the annotation necessary to approach this problem, but today's methods still struggle with the differences between artificial and real 3D data. We conjecture that one of the causes of this issue is the fact that today's methods learn directly from point coordinates, which makes them highly sensitive to scale changes. We propose to learn from a graph of reproducible object parts whose scale is more reliable. In combination with a voting scheme, our approach achieves significantly more robust classification and improves upon state-of-the-art by up to 16% when transferring from artificial to real objects.
dc.language	English
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation.ispartof	IEEE Robotics and Automation Letters
dc.relation.isbasedon	10.1109/LRA.2022.3186745
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0913 Mechanical Engineering
dc.title	Robust Sim2Real 3D Object Classification Using Graph Representations and a Deep Center Voting Scheme
dc.type	Journal Article
utslib.citation.volume	7
utslib.for	0913 Mechanical Engineering
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Mechanical and Mechatronic Engineering
utslib.copyright.status	closed_access	*
dc.date.updated	2023-03-17T05:33:04Z
pubs.issue	3
pubs.publication-status	Published
pubs.volume	7
utslib.citation.issue	3

Abstract:

While object semantic understanding is essential for service robotic tasks, 3D object classification is still an open problem. Learning from artificial 3D models alleviates the cost of the annotation necessary to approach this problem, but today's methods still struggle with the differences between artificial and real 3D data. We conjecture that one of the causes of this issue is the fact that today's methods learn directly from point coordinates, which makes them highly sensitive to scale changes. We propose to learn from a graph of reproducible object parts whose scale is more reliable. In combination with a voting scheme, our approach achieves significantly more robust classification and improves upon state-of-the-art by up to 16% when transferring from artificial to real objects.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/167483