Meta-USR: A Unified Super-Resolution Network for Multiple Degradation Parameters
文献类型：期刊论文
| 作者 | Hu, Xuecai1; Zhang, Zhang2,3 ; Shan, Caifeng4,5; Wang, Zilei1; Wang, Liang2,3; Tan, Tieniu2,3
|
| 刊名 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
 |
| 出版日期 | 2021-09-01 |
| 卷号 | 32期号:9页码:4151-4165 |
| ISSN号 | 2162-237X |
| 关键词 | Degradation Kernel Noise level Convolution Spatial resolution Imaging Arbitrary degradation blur kernel deep learning meta-learning scale factor super-resolution |
| DOI | 10.1109/TNNLS.2020.3016974 |
| 通讯作者 | Zhang, Zhang(zzhang@nlpr.ia.ac.cn) |
| 英文摘要 | Recent research on single image super-resolution (SISR) has achieved great success due to the development of deep convolutional neural networks. However, most existing SISR methods merely focus on super-resolution of a single fixed integer scale factor. This simplified assumption does not meet the complex conditions for real-world images which often suffer from various blur kernels or various levels of noise. More importantly, previous methods lack the ability to cope with arbitrary degradation parameters (scale factors, blur kernels, and noise levels) with a single model. A few methods can handle multiple degradation factors, e.g., noninteger scale factors, blurring, and noise, simultaneously within a single SISR model. In this work, we propose a simple yet powerful method termed meta-USR which is the first unified super-resolution network for arbitrary degradation parameters with meta-learning. In Meta-USR, a meta-restoration module (MRM) is proposed to enhance the traditional upscale module with the capability to adaptively predict the weights of the convolution filters for various combinations of degradation parameters. Thus, the MRM can not only upscale the feature maps with arbitrary scale factors but also restore the SR image with different blur kernels and noise levels. Moreover, the lightweight MRM can be placed at the end of the network, which makes it very efficient for iteratively/repeatedly searching the various degradation factors. We evaluate the proposed method through extensive experiments on several widely used benchmark data sets on SISR. The qualitative and quantitative experimental results show the superiority of our Meta-USR. |
| 资助项目 | National Key Research and Development Program of China[2016YFB1001002] ; Shandong Provincial Key Research and Development Program (Major Scientific and Technological Innovation Project)[2019JZZY010119] ; Shandong Provincial Key Research and Development Program (Major Scientific and Technological Innovation Project)[2019-001] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| WOS记录号 | WOS:000692208800033 |
| 资助机构 | National Key Research and Development Program of China ; Shandong Provincial Key Research and Development Program (Major Scientific and Technological Innovation Project) |
| 源URL | [http://ir.ia.ac.cn/handle/173211/45920]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 通讯作者 | Zhang, Zhang |
| 作者单位 | 1.Univ Sci & Technol China, Sch Informat Sci & Technol, Hefei 230026, Peoples R China 2.Chinese Acad Sci, Ctr Res Intelligent Percept & Comp, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China 4.Shandong Univ Sci & Technol, Coll Elect Engn & Automat, Qingdao 266590, Peoples R China 5.Chinese Acad Sci, Artificial Intelligence Res, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Hu, Xuecai,Zhang, Zhang,Shan, Caifeng,et al. Meta-USR: A Unified Super-Resolution Network for Multiple Degradation Parameters[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2021,32(9):4151-4165. |
| APA | Hu, Xuecai,Zhang, Zhang,Shan, Caifeng,Wang, Zilei,Wang, Liang,&Tan, Tieniu.(2021).Meta-USR: A Unified Super-Resolution Network for Multiple Degradation Parameters.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,32(9),4151-4165. |
| MLA | Hu, Xuecai,et al."Meta-USR: A Unified Super-Resolution Network for Multiple Degradation Parameters".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 32.9(2021):4151-4165. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。