基于锯齿空洞残差卷积的单幅图像超分辨率重建研究

李岚; 蔺国梁; 马少斌

doi:10.13568/j.cnki.651094.651316.2020.07.30.0002

您当前的位置：

首页 >

文章列表页 >

基于锯齿空洞残差卷积的单幅图像超分辨率重建研究

更新时间：2026-01-21

- 基于锯齿空洞残差卷积的单幅图像超分辨率重建研究
- Journal of Xinjiang University (Natural Science Edition in Chinese and English) Vol. 38, Issue 2, Pages: 174-190(2021)
- 作者机构：
  
  兰州文理学院数字媒体学院
- 作者简介：
- 基金信息：
- DOI：10.13568/j.cnki.651094.651316.2020.07.30.0002
  CLC： TP391.41;TP183
- Published：2021
- 稿件说明：
移动端阅览
[1]李岚,蔺国梁,马少斌.基于锯齿空洞残差卷积的单幅图像超分辨率重建研究[J].新疆大学学报(自然科学版)(中英文),2021,38(02):174-190.
[1]李岚,蔺国梁,马少斌.基于锯齿空洞残差卷积的单幅图像超分辨率重建研究[J].新疆大学学报(自然科学版)(中英文),2021,38(02):174-190. DOI： 10.13568/j.cnki.651094.651316.2020.07.30.0002.

DOI：10.13568/j.cnki.651094.651316.2020.07.30.0002.

摘要

针对残差学习的超分辨率重建方法中存在感受野受限、分辨率低、复杂性较高、边缘信息丢失等问题

提出一种锯齿空洞残差卷积的神经网络.首先

基于Res Net网络设计了锯齿空洞卷积

扩大网络的感受野

消除网络的"网格化"

并增加跳跃连接

将图像特征传递到更深的网路;然后

通过最后一个卷积层得到与原始图像大小相等的残差图像;最后

将输入LR图像与残差图像进行线性融合输出最终的超分辨率图像.在set5和set14数据集上的实验数据表明:与现有算法相比

本文算法具有更好的重建效果

学习性能有较大提高.

Abstract

In order to solve the problems of the limited receptive field

low-resolution

high complexity and loss of edge information in the super-resolution reconstruction method of residual learning

adilated residual convolution neural network is proposed. Firstly

we design the sawtooth dilated convolution based on the Res Net network to expand the receptive field of the network and eliminate the "zero filling" of the network

the image features are transferred to the deeper network by adding the jump connection. Secondly

the residual image with the same size as the original image is obtained through the last convolution layer. Finally

the input LR image and the residual image are linearly fused to output the final super-resolution image. The experimental data on set 5 and set 14 shows that compared with the existing algorithms

the algorithm of this paper has better reconstruction effect and better learning performance.

关键词

Keywords

references

苏衡,周杰,张志浩.图像超分辨率重建方法综述[J].自动化学报,2013,39(8):1202-1213.

杨东旭,赖惠成,班俊硕,等.基于改进DCNN结合迁移学习的图像分类方法[J].新疆大学学报(自然科学版),2018,35(2):195-202.

THEVENAZ P,Blu T,UNSER M.Handbook of Medical Imaging Processing and Analysis[M].[S.l.]:Academic Press,2000.

王知人,谷昊晟,任福全,等.基于深度卷积残差学习的图像超分辨[J].郑州大学学报(理学版),2020,53(3):42-48.

雷为民,王玉楠,李锦环.基于FSRCNN的图像超分辨率重建算法优化研究[J].传感器与微系统,2020,39(2):54-57．

周雷,阿里甫·库尔班,吕情深,等.新疆大学软件学院基于R-FCN的中国手指语识别[J].新疆大学学报(自然科学版)(中英文),2020,37(2):170-176.

张圣祥,郑力新,朱建清,等.采用深度学习的快速超分辨率图像重建方法[J].华侨大学学报(自然科学版),2019,40(2):245-250.

DONG C,LOY C C,HE K,et al.Image super-resolution using deep convolutional networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(2):295-307.

KIM J,KWON L J,MU L.Accurate image super-resolution using very deep convolutional networks[C]//Proceedings of the IEEEConference on Computer Vision and Pattern Recognition.Las Vegas:IEEE,2016:1646-1654.

YANG J C,WRIGHT J,HUANG T S,et al.Image super-resolution via sparse representation[J].IEEE Transactions on Image Processing,2010,19(11):2861-2873.

TAI Y,YANG J,LIU X.Image super-resolution via deep recursive residual network[C]//IEEE Computer Vision and Pattern Recognition (CVPR 2017).IEEE,2017.DOI:10.1109.

HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition.2016:770-778.[DOI:10.1109/CVPR.2016.90]

YANG Z,ZHANG K,LIANG Y,et al.Single image super-resolution with a parameter economic residual-like convolutional neural network[C]//International Conference on Multimedia Modeling.Springer,Cham,2017:353-364.

SHI W,CABALLERO J,HUSZAR F,et al.Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE,2016:1874-1883.

DONG C,CHEN C L,HE K,et al.Learning a deep convolutional network for image super-resolution[C]//European Conference on Computer Vision.Cham:Springer International Publishing,2014:184-199.

李岚,张云,马少斌.改进的梯度与肤色融合均值移动粒子滤波人脸跟踪[J].延边大学学报(自然科学版),2018,44(2):139-142.

K D,BA J.Adam:A method for stochastic optimization[C]//The International Conference on Learning Representations,San Diego,USA,2015.

Views

173

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Apnea Detection Based on 1D-Res&SENet

面向水下环境的海洋生物轻量化目标检测模型

温度引导的CNN-Transformer红外与可见光图像融合方法

遗传算法在瞬变电磁深度学习反演中的优化策略

基于无参注意力和联合损失的行人重识别

Related Author

Liu Jizhong

Shan Xinying

Hu Shaowen

Xu Jiahao

周铁军

王博

田生伟

王哲

Related Institution

National Research Center for Rehabilitation Technical Aids, Ministry of Civil Affairs of the People's Republic of China

Jiangxi Provincial Science and Technology Infrastructure Platform Center

School of Advanced Manufacturing Institute, Nanchang University

国家计算机网络与信息安全管理中心新疆分中心

新疆大学软件学院

⁰