Single-image super-resolution via joint statistic models-guided deep auto-encoder network

doi:10.1007/s00521-018-3886-2

CORC > 兰州理工大学 > 兰州理工大学

	Single-image super-resolution via joint statistic models-guided deep auto-encoder network
	Chen, Rong 1,4; Qu, Yanyun 1; Li, Cuihua 1; Zeng, Kun 2; Xie, Yuan 3; Li, Ce 5
刊名	Neural Computing and Applications
	2020-05-01
卷号	32 期号:9 页码:4885-4896
关键词	Benchmarking Deep neural networks Image denoising Image resolution Iterative methods Network coding Optical resolving power Signal to noise ratio Non-local similarities Peak signal to noise ratio Regularization framework Single images Split Bergman iteration Split bregman iterations Steering kernel regressions Total variation regularization
ISSN号	09410643
DOI	10.1007/s00521-018-3886-2
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. © 2018, Springer-Verlag London Ltd., part of Springer Nature.
WOS研究方向	Computer Science
语种	英语
出版者	Springer
WOS记录号	WOS:000527419900049
内容类型	期刊论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/115527]
专题	兰州理工大学
作者单位	1.School of Information Science and Engineering, Xiamen University, Xiamen, China; 2.College of Electronic Science and Technology, Xiamen University, Xiamen, China; 3.Research Center of Precision Sensing and Control, Institute of Automation, Chinese Academy of Sciences, Beijing, China; 4.College of Information Engineering, Xizang Minzu University, Xianyang, China; 5.New Energy School, Lanzhou University of Technology, Lanzhou, 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 and 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 and 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 and Applications 32.9(2020):4885-4896.