Knowledge Commons of Institute of Automation,CAS
Joint image-to-image translation with denoising using enhanced generative adversarial networks | |
Yan, Lan1,2![]() ![]() ![]() | |
发表期刊 | SIGNAL PROCESSING-IMAGE COMMUNICATION
![]() |
ISSN | 0923-5965 |
2021-02-01 | |
卷号 | 91页码:9 |
摘要 | Impressive progress has been made recently in image-to-image translation using generative adversarial networks (GANs). However, existing methods often fail in translating source images with noise to target domain. To address this problem, we joint image-to-image translation with image denoising and propose an enhanced generative adversarial network (EGAN). In particular, built upon pix2pix, we introduce residual blocks in the generator network to capture deeper multi-level information between source and target image distribution. Moreover, a perceptual loss is proposed to enhance the performance of image-to-image translation. As demonstrated through extensive experiments, our proposed EGAN can alleviate effects of noise in source images, and outperform other state-of-the-art methods significantly. Furthermore, we experimentally indicate that the proposed EGAN is also effective when applied to image denoising. |
关键词 | Image-to-image translation Generative adversarial networks Image enhancement Image denoising |
DOI | 10.1016/j.image.2020.116072 |
关键词[WOS] | SPARSE |
收录类别 | SCI |
语种 | 英语 |
资助项目 | Key Research and Development Program of Guangzhou, China[202007050002] ; National Natural Science Foundation of China[61806198] ; National Natural Science Foundation of China[61533019] ; National Natural Science Foundation of China[U1811463] |
项目资助者 | Key Research and Development Program of Guangzhou, China ; National Natural Science Foundation of China |
WOS研究方向 | Engineering |
WOS类目 | Engineering, Electrical & Electronic |
WOS记录号 | WOS:000603566200002 |
出版者 | ELSEVIER |
七大方向——子方向分类 | 图像视频处理与分析 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/42530 |
专题 | 多模态人工智能系统全国重点实验室_平行智能技术与系统团队 |
通讯作者 | Gou, Chao |
作者单位 | 1.Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 3.Xi An Jiao Tong Univ, Sch Software Engn, Xian, Peoples R China 4.Sun Yat Sen Univ, Sch Intelligent Syst Engn, Guangzhou, Peoples R China |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Yan, Lan,Zheng, Wenbo,Wang, Fei-Yue,et al. Joint image-to-image translation with denoising using enhanced generative adversarial networks[J]. SIGNAL PROCESSING-IMAGE COMMUNICATION,2021,91:9. |
APA | Yan, Lan,Zheng, Wenbo,Wang, Fei-Yue,&Gou, Chao.(2021).Joint image-to-image translation with denoising using enhanced generative adversarial networks.SIGNAL PROCESSING-IMAGE COMMUNICATION,91,9. |
MLA | Yan, Lan,et al."Joint image-to-image translation with denoising using enhanced generative adversarial networks".SIGNAL PROCESSING-IMAGE COMMUNICATION 91(2021):9. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Joint image-to-image(4437KB) | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论