SDALIE-GAN: Structure and Detail Aware GAN for Low-light Image Enhancement

Simple item page
dc.contributor.authorPang, Youxinen_US
dc.contributor.authorYuan, Mengkeen_US
dc.contributor.authorChang, Yuchunen_US
dc.contributor.authorYan, Dong-Mingen_US
dc.contributor.editorLee, Sung-Hee and Zollmann, Stefanie and Okabe, Makoto and Wünsche, Burkharden_US
dc.date.accessioned2021-10-14T10:05:46Z
dc.date.available2021-10-14T10:05:46Z
dc.date.issued2021
dc.description.abstractWe present a GAN-based network architecture for low-light image enhancement, called Structure and Detail Aware Low-light Image Enhancement GAN (SDALIE-GAN), which is trained with unpaired low/normal-light images. Specifically, complementary Structure Aware Generator (SAG) and Detail Aware Generator (DAG) are designed respectively to generate an enhanced low-light image. Besides, intermediate features from SAG and DAG are integrated through guided map supervised feature attention fusion module, and regularizes the generated samples with an appended intensity adjusting module. We demonstrate the advantages of the proposed approach by comparing it with state-of-the-art low-light image enhancement methods.en_US
dc.description.sectionheadersWorks-In-Progress and Posters
dc.description.seriesinformationPacific Graphics Short Papers, Posters, and Work-in-Progress Papers
dc.identifier.doi10.2312/pg.20211393
dc.identifier.isbn978-3-03868-162-5
dc.identifier.pages69-70
dc.identifier.urihttps://doi.org/10.2312/pg.20211393
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/pg20211393
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subjectComputational photography
dc.titleSDALIE-GAN: Structure and Detail Aware GAN for Low-light Image Enhancementen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
069-070.pdf
Size:
10.01 MB
Format:
Adobe Portable Document Format
Download
Collections
PG2021 Short Papers, Posters, and Work-in-Progress Papers