A TransISP Based Image Enhancement Method for Visual Disbalance in Low-light Images

Simple item page
dc.contributor.authorWu, Jiaqien_US
dc.contributor.authorGuo, Jingen_US
dc.contributor.authorJing, Ruien_US
dc.contributor.authorZhang, Shihaoen_US
dc.contributor.authorTian, Zijianen_US
dc.contributor.authorChen, Weien_US
dc.contributor.authorWang, Zehuaen_US
dc.contributor.editorChen, Renjieen_US
dc.contributor.editorRitschel, Tobiasen_US
dc.contributor.editorWhiting, Emilyen_US
dc.date.accessioned2024-10-13T18:07:17Z
dc.date.available2024-10-13T18:07:17Z
dc.date.issued2024
dc.description.abstractExisting image enhancement algorithms often fail to effectively address issues of visual disbalance, such as brightness unevenness and color distortion, in low-light images. To overcome these challenges, we propose a TransISP-based image enhancement method specifically designed for low-light images. To mitigate color distortion, we design dual encoders based on decoupled representation learning, which enable complete decoupling of the reflection and illumination components, thereby preventing mutual interference during the image enhancement process. To address brightness unevenness, we introduce CNNformer, a hybrid model combining CNN and Transformer. This model efficiently captures local details and long-distance dependencies between pixels, contributing to the enhancement of brightness features across various local regions. Additionally, we integrate traditional image signal processing algorithms to achieve efficient color correction and denoising of the reflection component. Furthermore, we employ a generative adversarial network (GAN) as the overarching framework to facilitate unsupervised learning. The experimental results show that, compared with six SOTA image enhancement algorithms, our method obtains significant improvement in evaluation indexes (e.g., on LOL, PSNR: 15.59%, SSIM: 9.77%, VIF: 9.65%), and it can improve visual disbalance defects in low-light images captured from real-world coal mine underground scenarios.en_US
dc.description.number7
dc.description.sectionheadersImage and Video Enhancement I
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume43
dc.identifier.doi10.1111/cgf.15209
dc.identifier.issn1467-8659
dc.identifier.pages12 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.15209
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf15209
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies → Computer vision problems; Image processing; Visibility
dc.subjectComputing methodologies → Computer vision problems
dc.subjectImage processing
dc.subjectVisibility
dc.titleA TransISP Based Image Enhancement Method for Visual Disbalance in Low-light Imagesen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
cgf15209.pdf
Size:
11.96 MB
Format:
Adobe Portable Document Format
Download
Collections
43-Issue 7