Lanzhou University of Technology Institutional Repository (LUT_IR)
Fine-grained image inpainting with scale-enhanced generative adversarial network | |
Liu, Weirong1; Cao, Chengrui1; Liu, Jie2; Ren, Chenwen1; Wei, Yulin1; Guo, Honglin3 | |
2021-03 | |
发表期刊 | PATTERN RECOGNITION LETTERS |
ISSN | 0167-8655 |
卷号 | 143页码:81-87 |
摘要 | With the emergence of Generative Adversarial Networks, great progress has been made in image inpainting. However, most existing methods can produce plausible results, but fail to generate finer textures and structures. This is mainly due to the fact that (1) the generation of finer content in the masked region of an image is not constrained enough during network training, and (2) many different alternative pixels are exist to fill in the masked regions, making it very difficult for the inpainting network to generate reasonable sharp edges. To address these issues, we propose a Scale Enhanced GAN (SE-GAN) model which combines the constraints of large- and small-scale receptive fields of our tailor-made discriminators to achieve fine-grained constraint on image details, a novel edge loss to further ensure the sharpness of the generated image. Experiments on multiple datasets including faces(CelebA-HQ), textures(DTD), buildings(Facade) and natural images(ImageNet, Places2) show that our approach can generate higher quality inpainting results with more details than previous methods. (c) 2021 Elsevier B.V. All rights reserved. |
关键词 | Generative adversarial networks Fine-grained constraint Edge loss |
DOI | 10.1016/j.patrec.2020.12.008 |
收录类别 | SCIE |
语种 | 英语 |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000615785700012 |
出版者 | ELSEVIER |
EI入藏号 | 20210509869479 |
EI主题词 | Image enhancement |
来源库 | WOS |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | https://ir.lut.edu.cn/handle/2XXMBERH/147451 |
专题 | 党委教师工作部(人事处、教师发展中心) |
通讯作者 | Liu, Weirong |
作者单位 | 1.Lanzhou Univ Technol, Coll Elect & Informat Engn, Lanzhou, Gansu, Peoples R China; 2.Lanzhou Univ Technol, Natl Demonstrat Ctr Expt Elect & Control Engn Edu, Lanzhou, Gansu, Peoples R China; 3.Tianshui Elect Dr Res Inst Grp CO LTD, Tianshui, Gansu, Peoples R China |
第一作者单位 | 电气工程与信息工程学院 |
通讯作者单位 | 电气工程与信息工程学院 |
第一作者的第一单位 | 电气工程与信息工程学院 |
推荐引用方式 GB/T 7714 | Liu, Weirong,Cao, Chengrui,Liu, Jie,et al. Fine-grained image inpainting with scale-enhanced generative adversarial network[J]. PATTERN RECOGNITION LETTERS,2021,143:81-87. |
APA | Liu, Weirong,Cao, Chengrui,Liu, Jie,Ren, Chenwen,Wei, Yulin,&Guo, Honglin.(2021).Fine-grained image inpainting with scale-enhanced generative adversarial network.PATTERN RECOGNITION LETTERS,143,81-87. |
MLA | Liu, Weirong,et al."Fine-grained image inpainting with scale-enhanced generative adversarial network".PATTERN RECOGNITION LETTERS 143(2021):81-87. |
条目包含的文件 | 条目无相关文件。 |
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