Shadow Removal via Cascade Large Mask Inpainting

Simple item page
dc.contributor.authorKim, Juwanen_US
dc.contributor.authorKim, Seung-Heonen_US
dc.contributor.authorJang, Insungen_US
dc.contributor.editorYang, Yinen_US
dc.contributor.editorParakkat, Amal D.en_US
dc.contributor.editorDeng, Bailinen_US
dc.contributor.editorNoh, Seung-Taken_US
dc.date.accessioned2022-10-04T06:38:03Z
dc.date.available2022-10-04T06:38:03Z
dc.date.issued2022
dc.description.abstractWe present a novel shadow removal framework based on the image inpainting approach. The proposed method consists of two cascade Large-Mask inpainting(LaMa) networks for shadow inpainting and edge inpainting. Experiments with the ISTD and adjusted ISTD dataset show that our method achieves competitive shadow removal results compared to state-of-the methods. And we also show that shadows are well removed from complex and large shadow images, such as urban aerial images.en_US
dc.description.sectionheadersImage Restoration
dc.description.seriesinformationPacific Graphics Short Papers, Posters, and Work-in-Progress Papers
dc.identifier.doi10.2312/pg.20221246
dc.identifier.isbn978-3-03868-190-8
dc.identifier.pages49-50
dc.identifier.pages2 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20221246
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/pg20221246
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Image processing; Image representations
dc.subjectComputing methodologies → Image processing
dc.subjectImage representations
dc.titleShadow Removal via Cascade Large Mask Inpaintingen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
049-050.pdf
Size:
2.42 MB
Format:
Adobe Portable Document Format
Download
Collections
PG2022 Short Papers, Posters, and Work-in-Progress Papers