Shadow Removal via Cascade Large Mask Inpainting
Loading...
Date
2022
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
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.
Description
CCS Concepts: Computing methodologies → Image processing; Image representations
@inproceedings{10.2312:pg.20221246,
booktitle = {Pacific Graphics Short Papers, Posters, and Work-in-Progress Papers},
editor = {Yang, Yin and Parakkat, Amal D. and Deng, Bailin and Noh, Seung-Tak},
title = {{Shadow Removal via Cascade Large Mask Inpainting}},
author = {Kim, Juwan and Kim, Seung-Heon and Jang, Insung},
year = {2022},
publisher = {The Eurographics Association},
ISBN = {978-3-03868-190-8},
DOI = {10.2312/pg.20221246}
}