Image Inpainting Using MSCSWin Transformer and Color Correction

Bo-Wei Chen, Tsung-Jung Liu, Kuan-Hsien Liu
{"title":"Image Inpainting Using MSCSWin Transformer and Color Correction","authors":"Bo-Wei Chen, Tsung-Jung Liu, Kuan-Hsien Liu","doi":"10.1109/ICCE-Taiwan58799.2023.10226944","DOIUrl":null,"url":null,"abstract":"Image inpainting has been researched for many years. From traditional methods to current CNN models, they all pursue two targets (structural stability and texture consistency). In this paper, we propose the multi-shift CSWin Transformer (MSCSWin Transformer) and the HSV loss to focus on colors to inpaint images for these two targets. At last, we compare our model with state-of-the-art methods on the Places2 dataset to confirm our proposed module is indeed working.","PeriodicalId":112903,"journal":{"name":"2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCE-Taiwan58799.2023.10226944","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Image inpainting has been researched for many years. From traditional methods to current CNN models, they all pursue two targets (structural stability and texture consistency). In this paper, we propose the multi-shift CSWin Transformer (MSCSWin Transformer) and the HSV loss to focus on colors to inpaint images for these two targets. At last, we compare our model with state-of-the-art methods on the Places2 dataset to confirm our proposed module is indeed working.
使用MSCSWin变压器和颜色校正的图像绘制
图像绘画已经被研究了很多年。从传统的方法到现在的CNN模型,都追求两个目标(结构稳定性和纹理一致性)。在本文中,我们提出了多移CSWin变压器(MSCSWin变压器)和HSV损失来聚焦颜色来绘制这两个目标的图像。最后,我们将我们的模型与Places2数据集上最先进的方法进行比较,以确认我们提出的模块确实有效。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信