Kim, JuwanKim, Seung-HeonJang, InsungYang, YinParakkat, Amal D.Deng, BailinNoh, Seung-Tak2022-10-042022-10-042022978-3-03868-190-8https://doi.org/10.2312/pg.20221246https://diglib.eg.org:443/handle/10.2312/pg20221246We 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.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies → Image processing; Image representationsComputing methodologies → Image processingImage representations10.2312/pg.2022124649-502 pages