Camera Tripod Removal Model in Panoramic Images Based on Generative Adversarial Networks

Jian Wu Jian Wu, Honghui Deng Jian Wu, Fei Cheng Honghui Deng, Hongjun Wang Fei Cheng
{"title":"Camera Tripod Removal Model in Panoramic Images Based on Generative Adversarial Networks","authors":"Jian Wu Jian Wu, Honghui Deng Jian Wu, Fei Cheng Honghui Deng, Hongjun Wang Fei Cheng","doi":"10.53106/199115992023063403002","DOIUrl":null,"url":null,"abstract":"\n There are often residual images of the camera tripod in panoramic images, which may reduce the image quality and deteriorate the post-processing speed. To address this problem, a camera tripod removal network (TRNet) based on generative adversarial network is proposed. As an end-to-end model, the generator is designed to include recognition and reconstruction branches, which reduce the number of parameters and improve the training efficiency by sharing the encoder and correspond to scaffold recognition and texture reconstruction respectively. The recognition branch based on the U-Net structure can effectively identify the tripod area, while the reconstruction branch can brilliantly reconstruct the texture details through an intermediate layer formed by stacking dilated convolution residual blocks. Furthermore, spectral normalized Markov discriminator and multiple combined loss function are adopted to promote global texture consistency and thus result in a better texture filling effect. Finally, a data set of 400 panoramic images is constructed and experimental results on this data set demonstrate the better repair ability of TRNet against other state-of-the-art methods.\n \n","PeriodicalId":345067,"journal":{"name":"電腦學刊","volume":"81 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"電腦學刊","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.53106/199115992023063403002","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

There are often residual images of the camera tripod in panoramic images, which may reduce the image quality and deteriorate the post-processing speed. To address this problem, a camera tripod removal network (TRNet) based on generative adversarial network is proposed. As an end-to-end model, the generator is designed to include recognition and reconstruction branches, which reduce the number of parameters and improve the training efficiency by sharing the encoder and correspond to scaffold recognition and texture reconstruction respectively. The recognition branch based on the U-Net structure can effectively identify the tripod area, while the reconstruction branch can brilliantly reconstruct the texture details through an intermediate layer formed by stacking dilated convolution residual blocks. Furthermore, spectral normalized Markov discriminator and multiple combined loss function are adopted to promote global texture consistency and thus result in a better texture filling effect. Finally, a data set of 400 panoramic images is constructed and experimental results on this data set demonstrate the better repair ability of TRNet against other state-of-the-art methods.  
基于生成对抗网络的全景图像相机三脚架去除模型
在全景图像中经常会有相机三脚架残留的图像,这可能会降低图像质量,降低后期处理速度。为了解决这一问题,提出了一种基于生成对抗网络的相机三脚架移除网络(TRNet)。作为端到端模型,该生成器包含识别和重建分支,通过共享编码器减少了参数数量,提高了训练效率,并分别对应于支架识别和纹理重建。基于U-Net结构的识别分支可以有效地识别三脚架区域,而重建分支通过扩展卷积残差块叠加形成的中间层,可以出色地重建纹理细节。此外,采用谱归一化马尔可夫鉴别器和多重组合损失函数来提高纹理的全局一致性,从而获得更好的纹理填充效果。最后,构建了一个包含400张全景图像的数据集,在该数据集上的实验结果表明,与其他最先进的方法相比,TRNet具有更好的修复能力。
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:604180095
Book学术官方微信