Decoupled Cross-Scale Cross-View Interaction for Stereo Image Enhancement in the Dark

Zheng, H; Zhang, Z; Fan, J; Hong, R; Yang, Y; Yan, S

Decoupled Cross-Scale Cross-View Interaction for Stereo Image Enhancement in the Dark

Zheng, H Zhang, Z Fan, J Hong, R Yang, Y

Yan, S

Permalink

Publisher:: ACM
Publication Type:: Conference Proceeding
Citation:: MM 2023 - Proceedings of the 31st ACM International Conference on Multimedia, 2023, pp. 1475-1484
Issue Date:: 2023-10-26

Closed Access

	Filename	Description	Size
	3581783.3611962.pdf	Published version	18.58 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	Zheng, H
dc.contributor.author	Zhang, Z
dc.contributor.author	Fan, J
dc.contributor.author	Hong, R
dc.contributor.author	Yang, Y https://orcid.org/0000-0002-0512-880X
dc.contributor.author	Yan, S
dc.date	2023-10-29
dc.date.accessioned	2024-06-09T08:18:32Z
dc.date.available	2024-06-09T08:18:32Z
dc.date.issued	2023-10-26
dc.identifier.citation	MM 2023 - Proceedings of the 31st ACM International Conference on Multimedia, 2023, pp. 1475-1484
dc.identifier.isbn	979-8-4007-0108-5
dc.identifier.uri	http://hdl.handle.net/10453/179463
dc.description.abstract	Low-light stereo image enhancement (LLSIE) aims at improving the visual quality of stereo images captured in dark conditions. However, existing methods have shown limited success in detail recovery and illumination adjustment. This can be attributed to two main factors: 1) insufficient single-scale inter-view interaction hinders the exploitation of valuable cross-view cues; 2) lacking long-range dependency leads to the inability to deal with the spatial long-range effects caused by illumination degradation. To address these limitations, we propose a novel LLSIE model named Decoupled Cross-Scale Cross-View Interaction Network (DCI-Net). Our model introduces a key component called the Decoupled Interaction Module (DIM) designed to promote sufficient dual-view information exchange. DIM decouples the dual-view information interaction by discovering multi-scale cross-view correlations and further exploring cross-scale information flow. Furthermore, we present Spatial-channel Information Mining Block (SIMB) for intra-view feature extraction, and the benefits are twofold. One is long-range dependency capture to build spatial long-range relationship, and the other is expanded channel information refinement that enhances information flow in the channel dimension. Extensive experiments conducted on Flickr1024, KITTI 2012, KITTI 2015, and Middlebury datasets show that our method obtains better illumination adjustment and detail recovery, and achieves SOTA performance compared to other related methods.
dc.language	en
dc.publisher	ACM
dc.relation.ispartof	MM 2023 - Proceedings of the 31st ACM International Conference on Multimedia
dc.relation.ispartof	ACM International Conference on Multimedia
dc.relation.isbasedon	10.1145/3581783.3611962
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Decoupled Cross-Scale Cross-View Interaction for Stereo Image Enhancement in the Dark
dc.type	Conference Proceeding
utslib.location.activity	Ottawa, Canada
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2024-06-09T08:18:22Z
pubs.finish-date	2023-11-03
pubs.place-of-publication	USA
pubs.publication-status	Published
pubs.start-date	2023-10-29
dc.location	USA

Abstract:

Low-light stereo image enhancement (LLSIE) aims at improving the visual quality of stereo images captured in dark conditions. However, existing methods have shown limited success in detail recovery and illumination adjustment. This can be attributed to two main factors: 1) insufficient single-scale inter-view interaction hinders the exploitation of valuable cross-view cues; 2) lacking long-range dependency leads to the inability to deal with the spatial long-range effects caused by illumination degradation. To address these limitations, we propose a novel LLSIE model named Decoupled Cross-Scale Cross-View Interaction Network (DCI-Net). Our model introduces a key component called the Decoupled Interaction Module (DIM) designed to promote sufficient dual-view information exchange. DIM decouples the dual-view information interaction by discovering multi-scale cross-view correlations and further exploring cross-scale information flow. Furthermore, we present Spatial-channel Information Mining Block (SIMB) for intra-view feature extraction, and the benefits are twofold. One is long-range dependency capture to build spatial long-range relationship, and the other is expanded channel information refinement that enhances information flow in the channel dimension. Extensive experiments conducted on Flickr1024, KITTI 2012, KITTI 2015, and Middlebury datasets show that our method obtains better illumination adjustment and detail recovery, and achieves SOTA performance compared to other related methods.

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

http://hdl.handle.net/10453/179463