arrow
返回

Edge Profile Super Resolution

delete2021-01-01
delete1
delete
OA
AI
J
Jiun Lee
I
Inyong Yun
J
Jaekwang Kim *
DOI:10.1109/ACCESS.2021.3108998delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
The purpose of single-image super resolution (SISR) is to reconstruct an accurate high-resolution image from a degraded low-resolution image. Owing to the lack of information in low-resolution images, SISR is a challenging problem. In particular, it is difficult to represent details, including high-frequency components, such as texture and structural information. We propose the edge profile super-resolution (EPSR) method to preserve structural information and restore texture. EPSR is achieved by stacking modified fractal residual network (mFRN) structures hierarchically and repeatedly. Each mFRN is composed of many residual edge profile blocks (REPBs) that extract features and preserve the edge, structure, and texture information of the image. For implementing REPB, we design three main modules: Residual Efficient Channel Attention Block(RECAB) module, Edge Profile(EP) module, and Context Network(CN) module. By repeating the procedure in the mFRN structure, the EPSR method could be used to extract high-fidelity features, thus preventing texture loss and preserving the structure with appropriate sharpness. Experimental results show that EPSR achieves competitive performance against state-of-the-art methods in terms of the peak signal-to-noise ratio(PSNR) and structural similarity index measure(SSIM) evaluation metrics, as well as visual results.
Keyword:
Image edge detection
Feature extraction
Iron
Image restoration
High frequency
Fractals
Deep learning
Image super-resolution
contextual information
edge
image structure
texture

期刊

IEEE Access 封面图
IEEE Access
IF:
3.6
论文数:
9.8W
被引数:
29.4W

机构

S
sungkyunkwan university (skku)
学者数:
3.7W
论文数: 3.6W
被引数: 49
引用论文

引用论文

Quantifying the Dynamics of COVID-19 Burden and Impact of Interventions in Java, Indonesia
err2021-01-01
err0
errOAAI
errBimandra Adiputra Djaafara; Charles Whittaker; Oliver J. Watson; Robert Verity; Nicholas F. Brazeau; Dwi Oktavia; Verry Adrian; Ngabila Salama; Sangeeta Bhatia; Pierre Nouvellet; Ellie Sherrard-Smith; Thomas S. Churcher; Henry Surendra; Rosa N. Lina; Lenny L. Ekawati; Karina D. Lestari; Adhi Andrianto; Guy Thwaites; J. Kevin Baird; Azra Ghani; Iqbal RF Elyazar; Patrick Walker
err分享
err收藏
Learning low-level vision
err2000-01-01
err1.2K
PREAI
errFreeman, WT; Pasztor, EC; Carmichael, OT
err分享
err收藏
Nurses’ Attitudes Towards People with Dementia: the semantic differential technique
err2006-05-01
err0
PREAI
errKarl-Gustaf Norbergh; Yvonne Helin; Annika Dahl; Ove Hellzén; Kenneth Asplund
err分享
err收藏
Left ventricular noncompaction (LVNC) and low mitochondrial membrane potential are specific for Barth syndrome
err2013-01-30
err0
errOAAI
errAgnieszka Karkucinska‐Wieckowska; Joanna Trubicka; Bozena Werner; Katarzyna Kokoszynska; Magdalena Pajdowska; Maciej Pronicki; Elzbieta Czarnowska; Magdalena Lebiedzinska; Jolanta Sykut‐Cegielska; Lidia Ziolkowska; Weronika Jaron; Anna Dobrzanska; Elzbieta Ciara; Mariusz R. Wieckowski; Ewa Pronicka
err分享
err收藏
No Evidence for Rapid Subtype C Spread within an Epidemic in Which Multiple Subtypes and Intersubtype Recombinants Circulate
err2005-12-01
err0
PREAI
errStephanie Rainwater; Shannon DeVange; Manish Sagar; J. Ndinya-Achola; Kishorchandra Mandaliya; Joan K. Kreiss; Julie Overbaugh
err分享
err收藏
学者 查看更多内容