中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 精密感知与控制研究中心
Single-image super-resolution via joint statistic models-guided deep auto-encoder network

文献类型：期刊论文

作者Chen, Rong1,5; Qu, Yanyun5; Li, Cuihua5; Zeng, Kun3; Xie, Yuan4; Li, Ce2
刊名NEURAL COMPUTING & APPLICATIONS
出版日期2020-05-01
卷号32期号:9页码:4885-4896
关键词Non-local similarity Split Bergman iteration Steering kernel regression Single-image super-resolution
ISSN号0941-0643
DOI10.1007/s00521-018-3886-2
通讯作者Qu, Yanyun(yyqu@xmu.edu.cn)
英文摘要Recent researches on super-resolution (SR) with deep learning networks have achieved amazing results. However, most of the existing studies neglect the internal distinctiveness of an image and the output of most methods tends to be of blurring, smoothness and implausibility. In this paper, we proposed a unified model which combines the deep model with the image restoration model for single-image SR. This model can not only reconstruct the SR image, but also keep the distinct fine structures for the low-resolution image. Two statistic priors are used to guide the updating of the output of the deep neural network: One is the non-local similarity and the other is the local smoothness. The former is modeled as the non-local total variation regularization, and the latter as the steering kernel regression total variation regularization. For this unified model, a new optimization function is formulated under a regularization framework. To optimize the total variation problem, a novel algorithm based on split Bregman iteration is developed with the theoretical proof of convergence. The experimental results demonstrate that the proposed unified model improves the peak signal-to-noise ratio of the deep SR model. Quantitative and qualitative results on four benchmark datasets show that the proposed model achieves better performance than the deep SR model without regularization terms.
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000527419900049
出版者SPRINGER LONDON LTD
源URL[http://ir.ia.ac.cn/handle/173211/39351]  
专题自动化研究所_精密感知与控制研究中心
通讯作者Qu, Yanyun
作者单位1.Xizang Minzu Univ, Coll Informat Engn, Xianyang, Peoples R China
2.Lanzhou Univ Technol, New Energy Sch, Lanzhou, Peoples R China
3.Xiamen Univ, Coll Elect Sci & Technol, Xiamen, Peoples R China
4.Chinese Acad Sci, Inst Automat, Res Ctr Precis Sensing & Control, Beijing, Peoples R China
5.Xiamen Univ, Sch Informat Sci & Engn, Xiamen, Peoples R China
推荐引用方式
GB/T 7714		 Chen, Rong,Qu, Yanyun,Li, Cuihua,et al. Single-image super-resolution via joint statistic models-guided deep auto-encoder network[J]. NEURAL COMPUTING & APPLICATIONS,2020,32(9):4885-4896.
APA Chen, Rong,Qu, Yanyun,Li, Cuihua,Zeng, Kun,Xie, Yuan,&Li, Ce.(2020).Single-image super-resolution via joint statistic models-guided deep auto-encoder network.NEURAL COMPUTING & APPLICATIONS,32(9),4885-4896.
MLA Chen, Rong,et al."Single-image super-resolution via joint statistic models-guided deep auto-encoder network".NEURAL COMPUTING & APPLICATIONS 32.9(2020):4885-4896.

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。