Few-Shot Stereo Matching with High Domain Adaptability Based on Adaptive Recursive Network

Wu, R; Wang, M; Li, Z; Zhou, J; Chen, F; Wang, X; Sun, C

Few-Shot Stereo Matching with High Domain Adaptability Based on Adaptive Recursive Network

Wu, R Wang, M Li, Z Zhou, J

Chen, F

Wang, X Sun, C

Permalink

Publisher:: SPRINGER
Publication Type:: Journal Article
Citation:: International Journal of Computer Vision, 2023
Issue Date:: 2023-01-01

Recently Added

	Filename	Description	Size
	2-s2.0-85178273677 AM.pdf	Accepted version	4.68 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is new to OPUS and is not currently available.

Full metadata record

Field	Value	Language
dc.contributor.author	Wu, R
dc.contributor.author	Wang, M
dc.contributor.author	Li, Z
dc.contributor.author	Zhou, J https://orcid.org/0000-0001-6034-644X
dc.contributor.author	Chen, F https://orcid.org/0000-0003-4971-8729
dc.contributor.author	Wang, X
dc.contributor.author	Sun, C
dc.date.accessioned	2024-03-11T23:27:21Z
dc.date.available	2024-03-11T23:27:21Z
dc.date.issued	2023-01-01
dc.identifier.citation	International Journal of Computer Vision, 2023
dc.identifier.issn	0920-5691
dc.identifier.issn	1573-1405
dc.identifier.uri	http://hdl.handle.net/10453/176504
dc.description.abstract	Deep learning based stereo matching algorithms have been extensively researched in areas such as robot vision and autonomous driving due to their promising performance. However, these algorithms require a large amount of labeled data for training and encounter inadequate domain adaptability, which degraded their applicability and flexibility. This work addresses the two deficiencies and proposes a few-shot trained stereo matching model with high domain adaptability. In the model, stereo matching is formulated as the problem of dynamic optimization in the possible solution space, and a multi-scale matching cost computation method is proposed to obtain the possible solution space for the application scenes. Moreover, an adaptive recurrent 3D convolutional neural network is designed to determine the optimal solution from the possible solution space. Experimental results demonstrate that the proposed model outperforms the state-of-the-art stereo matching algorithms in terms of training requirements and domain adaptability.
dc.language	English
dc.publisher	SPRINGER
dc.relation	Digital Finance CRC Limited
dc.relation.ispartof	International Journal of Computer Vision
dc.relation.isbasedon	10.1007/s11263-023-01953-0
dc.rights	info:eu-repo/semantics/restrictedAccess
dc.subject	0801 Artificial Intelligence and Image Processing
dc.subject.classification	Artificial Intelligence & Image Processing
dc.subject.classification	4603 Computer vision and multimedia computation
dc.subject.classification	4607 Graphics, augmented reality and games
dc.subject.classification	4611 Machine learning
dc.title	Few-Shot Stereo Matching with High Domain Adaptability Based on Adaptive Recursive Network
dc.type	Journal Article
utslib.for	0801 Artificial Intelligence and Image Processing
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	recently_added	*
dc.date.updated	2024-03-11T23:27:20Z
pubs.publication-status	Published

Abstract:

Deep learning based stereo matching algorithms have been extensively researched in areas such as robot vision and autonomous driving due to their promising performance. However, these algorithms require a large amount of labeled data for training and encounter inadequate domain adaptability, which degraded their applicability and flexibility. This work addresses the two deficiencies and proposes a few-shot trained stereo matching model with high domain adaptability. In the model, stereo matching is formulated as the problem of dynamic optimization in the possible solution space, and a multi-scale matching cost computation method is proposed to obtain the possible solution space for the application scenes. Moreover, an adaptive recurrent 3D convolutional neural network is designed to determine the optimal solution from the possible solution space. Experimental results demonstrate that the proposed model outperforms the state-of-the-art stereo matching algorithms in terms of training requirements and domain adaptability.

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

http://hdl.handle.net/10453/176504