Row–Column Separated Attention Based Low‐Light Image/Video Enhancement

Simple item page
dc.contributor.authorDong, Chengqien_US
dc.contributor.authorCao, Zhiyuanen_US
dc.contributor.authorQi, Tuoshien_US
dc.contributor.authorWu, Kexinen_US
dc.contributor.authorGao, Yixingen_US
dc.contributor.authorTang, Fanen_US
dc.contributor.editorAlliez, Pierreen_US
dc.contributor.editorWimmer, Michaelen_US
dc.date.accessioned2024-12-19T11:16:07Z
dc.date.available2024-12-19T11:16:07Z
dc.date.issued2024
dc.description.abstractU‐Net structure is widely used for low‐light image/video enhancement. The enhanced images result in areas with large local noise and loss of more details without proper guidance for global information. Attention mechanisms can better focus on and use global information. However, attention to images could significantly increase the number of parameters and computations. We propose a Row–Column Separated Attention module (RCSA) inserted after an improved U‐Net. The RCSA module's input is the mean and maximum of the row and column of the feature map, which utilizes global information to guide local information with fewer parameters. We propose two temporal loss functions to apply the method to low‐light video enhancement and maintain temporal consistency. Extensive experiments on the LOL, MIT Adobe FiveK image, and SDSD video datasets demonstrate the effectiveness of our approach.en_US
dc.description.number6
dc.description.sectionheadersMajor Revision from EG Symposium on Rendering
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume43
dc.identifier.doi10.1111/cgf.15192
dc.identifier.pages15 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.15192
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf15192
dc.publisher© 2024 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.en_US
dc.subjectLow‐light image/video enhancement
dc.subjectRow‐column separated attention
dc.subjectTemporal consistency
dc.titleRow–Column Separated Attention Based Low‐Light Image/Video Enhancementen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
25_cgf15192.pdf
Size:
5.32 MB
Format:
Adobe Portable Document Format
Download
Collections
43-Issue 6