Institutional Repository of Coll Elect & Informat Engn
Gradual deep residual network for super-resolution | |
Song, Zhaoyang1; Zhao, Xiaoqiang1,2,3; Jiang, Hongmei1,2,3 | |
2021-03 | |
发表期刊 | Multimedia Tools and Applications |
ISSN | 1380-7501 |
卷号 | 80期号:7页码:9765-9778 |
摘要 | Deep neural networks with single upsampling have achieved the improvement of performance for single image super-resolution. However, these networks lose a lot of details of low-resolution image in the reconstruction process. In this paper, we propose a gradual deep residual network for super-resolution (GDSR), which consists of multiple reconstruction network with 2 scale factor (2X reconstruction network). In 2X reconstruction network, a residual block connected by residual (RBR) is proposed to form a deep residual network, which is used to extract the depth features of low-resolution images; then the extracted features are upsampled into the features of high-resolution image by sub-pixel convolutional layer. GDSR gradually reconstructs high-quality high-resoluiton images from low-resolution images by multiple 2X reconstruction networks. Extensive experiments on benchmark datasets demonstrate that the proposed GDSR outperforms the state-of-the-art methods in terms of quantitative evaluation, visual evaluation, and execution time evaluation. © 2020, Springer Science+Business Media, LLC, part of Springer Nature. |
关键词 | Deep neural networks Image enhancement Optical resolving power Benchmark datasets High resolution image Low resolution images Quantitative evaluation Reconstruction networks Reconstruction process State-of-the-art methods Visual evaluation |
DOI | 10.1007/s11042-020-10152-9 |
收录类别 | SCI ; SCIE ; EI |
语种 | 英语 |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000589699900005 |
出版者 | Springer |
EI入藏号 | 20204809562610 |
EI主题词 | Image reconstruction |
EI分类号 | 741.1 Light/Optics |
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/148391 |
专题 | 电气工程与信息工程学院 |
通讯作者 | Zhao, Xiaoqiang |
作者单位 | 1.Lanzhou Univ Technol, Coll Elect Engn & Informat Engn, Lanzhou 730050, Peoples R China; 2.Key Lab Gansu Adv Control Ind Proc, Lanzhou 730050, Peoples R China; 3.Lanzhou Univ Technol, Natl Expt Teaching Ctr Elect & Control Engn, Lanzhou 730050, 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; 兰州理工大学 |
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 | Song, Zhaoyang,Zhao, Xiaoqiang,Jiang, Hongmei. Gradual deep residual network for super-resolution[J]. Multimedia Tools and Applications,2021,80(7):9765-9778. |
APA | Song, Zhaoyang,Zhao, Xiaoqiang,&Jiang, Hongmei.(2021).Gradual deep residual network for super-resolution.Multimedia Tools and Applications,80(7),9765-9778. |
MLA | Song, Zhaoyang,et al."Gradual deep residual network for super-resolution".Multimedia Tools and Applications 80.7(2021):9765-9778. |
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