ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Shadow Removal via Cascade Large Mask Inpainting
Cited - time in scopus Download 108 time Share share facebook twitter linkedin kakaostory
Authors
Juwan Kim, Seung-Heon Kim, Insung Jang
Issue Date
2022-10
Citation
Pacific Conference on Computer Graphics and Applications (Pacific Graphics) 2022, pp.49-50
Language
English
Type
Conference Paper
DOI
https://dx.doi.org/10.2312/pg.20221246
Abstract
We 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.
KSP Keywords
Aerial images, image inpainting(IMIN), shadow image, shadow removal
This work is distributed under the term of Creative Commons License (CCL)
(CC BY)
CC BY