arrow
返回

A Single-Image Super-Resolution Method Based on Progressive-Iterative Approximation

delete2020-06-01
delete26
PRE
AI
Y
Yunfeng Zhang
P
Ping Wang
张
张彩明 (Caiming Zhang)
蔺
蔺宏伟 (Hongwei Lin)
DOI:10.1109/TMM.2019.2943750delete
delete原文链接
delete分享
delete收藏
摘要

摘要

En 中文
In this paper, a novel single image super-resolution (SR) method based on progressive-iterative approximation is proposed. To preserve textures and clear edges, the image SR reconstruction is treated as an image progressive-iterative fitting procedure and achieved by iterative interpolation. Due to different features in different regions, we first employ the nonsubsampled contourlet transform (NSCT) to divide the image into smooth regions, texture regions, and edges. Then, a hybrid interpolation scheme based on curves and surfaces is proposed, which differs from the traditional surface interpolation methods. Specifically, smooth regions are interpolated by the non-uniform rational basis spline (NURBS) surface geometric iteration. To retain textures, control points are increased, and the progressive-iterative approximation of the NURBS surface is employed to interpolate the texture regions. By considering edges in an image as curve segments that are connected by pixels with dramatic changes, we use NURBS curve progressive-iterative approximation to interpolate the edges, which sharpens the edges and can maintain the image edge structure without jaggy and block artifacts. The experimental results demonstrate that the proposed method significantly outperforms the state-of-the-art methods in terms of both subjective and objective measures.
Keyword:
Image edge detection
Interpolation
Surface reconstruction
Image reconstruction
Splines (mathematics)
Surface topography
Surface texture
Single image super-resolution
regional division
surface geometric iteration
curve geometric iteration
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Transactions on Multimedia 封面图
IEEE Transactions on Multimedia
IF:
9.7
论文数:
5.3K
被引数:
3.4W

机构

E
ecole de technologie superieure - canada
学者数:
1.5K
论文数: 1.6K
被引数: 2.1K
U
university of technology – sydney
学者数:
18
论文数: 6
被引数: 0
U
university of quebec
学者数:
206
论文数: 103
被引数: 1.2W
山东大学 封面图
山东大学
学者数:
8.1K
论文数: 2.2K
被引数: 4.2W
学者 查看更多机构
引用论文

引用论文

Learning-Based Joint Super-Resolution and Deblocking for a Highly Compressed Image
err2015-07-01
err71
PREAI
errKang, Li-Wei; Hsu, Chih-Chung; Zhuang, Boqi; Lin, Chia-Wen; Yeh, Chia-Hung
err分享
err收藏
Fast Image Super-Resolution via Local Adaptive Gradient Field Sharpening Transform
err2018-04-01
err35
PREAI
errSong, Qiang; Xiong, Ruiqin; Liu, Dong; Xiong, Zhiwei; Wu, Feng; Gao, Wen
err分享
err收藏
Rotation expanded dictionary-based single image super-resolution
err2016-12-01
err15
PREAI
errLi, Tao; He, Xiaohai; Teng, Qizhi; Wu, Xiaoqiang
err分享
err收藏
Enhancement of Quicklime Dissolution in Steelmaking Slags by Utilizing Residual CO<sub>2</sub> from Quicklime
err2017-01-01
err0
errOAAI
errNobuhiro Maruoka; Akihisa Ito; Miho Hayasaka; Shin-ya Kitamura; Hiroshi Nogami
err分享
err收藏
err
IF0
err
err0
PREAI
err
err分享
err收藏
Statistical Model for Pressure Distribution of Bolted Joints
err2010-04-01
err0
PREAI
errMarcia B. H. Mantelli; Fernando H. Milanez; Eliete N. Pereira; Leroy S. Fletcher
err分享
err收藏
An Iterative Framework of Cascaded Deblocking and Superresolution for Compressed Images
err2018-06-01
err31
PREAI
errLi, Tao; He, Xiaohai; Qing, Linbo; Teng, Qizhi; Chen, Honggang
err分享
err收藏
学者 查看更多内容