Unsupervised real image super-resolution via knowledge distillation network
文献类型:期刊论文
作者 | Yuan, Nianzeng2; Sun, Bangyong2; Zheng, Xiangtao1 |
刊名 | COMPUTER VISION AND IMAGE UNDERSTANDING |
出版日期 | 2023-09 |
卷号 | 234 |
ISSN号 | 1077-3142;1090-235X |
关键词 | Super-resolution Knowledge distillation Degradation module Convolutional neural network |
DOI | 10.1016/j.cviu.2023.103736 |
产权排序 | 2 |
英文摘要 | Super-resolution convolutional neural networks recently have demonstrated high-quality restoration for single images. Despite existing methods have achieved remarkable performance based on synthetic datasets, the performance is poor on real-world or natural data. To address this issue, zero-shot super-resolution (ZSSR) has been proposed for adaptive learning. However, ZSSR is unable to keep the simulated degradation process consistent with the degradation kernel of the real degradation process. Furthermore, the learned mapping of ZSSR is different from the desired mapping. In this paper, an unsupervised image super-resolution via knowledge distillation network (USRKDN) is proposed. Specifically, the proposed degradation module generates an image-specific degradation kernel and corresponding degenerated images. Moreover, the knowledge distillation module is proposed to solve the issue that the mapping cannot be completely equivalent, which transfers the learned map by knowledge distillation. The full convolution module is also explored to help the reconstruction of information. Extensive experimental results on synthetic and real datasets demonstrate the effectiveness of USRKDN. In addition, USRKDN is proven to be good at reconstructing image details in real scenes, which provides an effective method for generating information learning tasks with fewer samples. |
语种 | 英语 |
出版者 | ACADEMIC PRESS INC ELSEVIER SCIENCE |
WOS记录号 | WOS:001024622400001 |
源URL | [http://ir.opt.ac.cn/handle/181661/96656] |
专题 | 西安光学精密机械研究所_光学影像学习与分析中心 |
通讯作者 | Zheng, Xiangtao |
作者单位 | 1.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Key Lab Spectral Imaging Technol CAS, Xian 710119, Shaanxi, Peoples R China 2.Xian Univ Technol, Sch Comp Sci & Engn, Xian 710048, Peoples R China |
推荐引用方式 GB/T 7714 | Yuan, Nianzeng,Sun, Bangyong,Zheng, Xiangtao. Unsupervised real image super-resolution via knowledge distillation network[J]. COMPUTER VISION AND IMAGE UNDERSTANDING,2023,234. |
APA | Yuan, Nianzeng,Sun, Bangyong,&Zheng, Xiangtao.(2023).Unsupervised real image super-resolution via knowledge distillation network.COMPUTER VISION AND IMAGE UNDERSTANDING,234. |
MLA | Yuan, Nianzeng,et al."Unsupervised real image super-resolution via knowledge distillation network".COMPUTER VISION AND IMAGE UNDERSTANDING 234(2023). |
入库方式: OAI收割
来源:西安光学精密机械研究所
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。