基于多残差网络的结构保持超分辨重建
Structure-Preserving Super-Resolution Reconstruction Based on Multi-residual Network
查看参考文献31篇
|
文摘
|
针对图像超分辨率重建中几何结构扭曲和细节缺失等问题,文中提出基于多残差网络的结构保持超分辨重建算法.在小波变换域和梯度域上进行深度学习.文中算法包含3种残差网络.残差梯度网络用于结构及边缘信息的重建.残差小波变换网络从整体上进行图像高频信息的重建.残差通道注意力网络通过调整网络注意力,着重学习重要的通道特征,从局部恢复图像高频信息,提高重建效率.实验表明,文中算法在定量结果和视觉效果方面均取得较优表现. |
|
其他语种文摘
|
Aiming at the problems of geometric structure distortion and missing details in image super-resolution reconstruction,a structure-preserving super-resolution reconstruction algorithm based on multi-residual network is proposed. Deep learning is carried out in the wavelet transform domain and the gradient domain. Three kinds of residual networks are introduced. The structure and the edge information are reconstructed by the residual gradient network. The high-frequency information of the image is reconstructed as a whole by the residual wavelet transform network. The network attention is adjusted by the residual channel attention network,the important channel features are emphatically learned,and the high frequency information of the image is recovered locally. Experiments show that the proposed algorithm achieves better performance in both quantitative results and visual effects. |
|
来源
|
模式识别与人工智能
,2021,34(3):232-240 【核心库】
|
|
DOI
|
10.16451/j.cnki.issn1003-6059.202103005
|
|
关键词
|
超分辨率重建
;
深度学习
;
多残差网络
;
结构保持
|
|
地址
|
1.
西安电子科技大学, 综合业务网理论及关键技术国家重点实验室, 西安, 710071
2.
中国科学院西安光学精密机械研究所, 中国科学院光谱成像技术重点实验室, 西安, 710119
3.
重庆邮电大学, 图像认知重庆市重点实验室, 重庆, 400065
|
|
语种
|
中文 |
|
文献类型
|
研究性论文 |
|
ISSN
|
1003-6059 |
|
学科
|
自动化技术、计算机技术 |
|
基金
|
国家自然科学基金青年科学基金
;
陕西省高校科协人才托举计划项目
;
中国科学院光谱成像技术重点实验室开放基金项目
;
中央基本科研业务费新教师创新项目
|
|
文献收藏号
|
CSCD:6962613
|
参考文献 共
31
共2页
|
|
1.
付利华. 基于运动特征融合的快速视频超分辨率重构方法.
模式识别与人工智能,2019,32(11):1022-1031
|
被引
2
次
|
|
|
|
|
2.
Ledig C. Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network.
Proc of the IEEE Conference on Computer Vision and Pattern Recognition,2017:105-114
|
被引
4
次
|
|
|
|
|
3.
Dong C. Accelerating the Super-Resolution Convolutional Neural Network.
Proc of the 14th European Conference on Computer Vision,2016:391-407
|
被引
3
次
|
|
|
|
|
4.
付利华. 融合参考图像的人脸超分辨率重构方法.
模式识别与人工智能,2020,33(4):325-336
|
被引
2
次
|
|
|
|
|
5.
Shi W Z. Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network.
Proc of the IEEE Conference on Computer Vision and Pattern Recognition,2016:1874-1883
|
被引
7
次
|
|
|
|
|
6.
Zou W W W. Very Low Resolution Face Recognition Problem.
Proc of the 4th IEEE International Conference on Biometrics: Theory,Applications and Systems,2010
|
被引
1
次
|
|
|
|
|
7.
Shi W Z. Cardiac Image Super-Resolution with Global Correspondence Using Multi-atlas Patch-Match.
Proc of the International Conference on Medical Image Computing and Computer Assisted Intervention,2013:9-16
|
被引
1
次
|
|
|
|
|
8.
郑少飞. 基于改进损失函数的多阶段行人属性识别方法.
模式识别与人工智能,2018,31(12):1085-1095
|
被引
2
次
|
|
|
|
|
9.
蒋桧慧. 融合直接度量和间接度量的行人再识别.
模式识别与人工智能,2018,31(2):167-174
|
被引
3
次
|
|
|
|
|
10.
刘丽. 改进YOLOv3网络结构的遮挡行人检测算法.
模式识别与人工智能,2020,33(6):568-574
|
被引
4
次
|
|
|
|
|
11.
Dong C. Learning a Deep Convolutional Network for Image Super-Resolution.
Proc of the European Conference on Computer Vision,2014:184-199
|
被引
8
次
|
|
|
|
|
12.
Kim J. Accurate Image Super-Resolution Using Very Deep Convolutional Networks.
Proc of the IEEE Conference on Computer Vision and Pattern Recognition,2016:1646-1654
|
被引
9
次
|
|
|
|
|
13.
Tai Z. Image Super-Resolution via Deep Recursive Residual Network.
Proc of the IEEE Conference on Computer Vision and Pattern Recognition,2017:2790-2798
|
被引
1
次
|
|
|
|
|
14.
Kim J. Deeply-Recursive Convolutional Network for Image Super-Resolution.
Proc of the IEEE Conference on Computer Vision and Pattern Recognition,2016:1637-1645
|
被引
7
次
|
|
|
|
|
15.
He K M. Deep Residual Learning for Image Recognition.
Proc of the IEEE Conference on Computer Vision and Pattern Recognition,2016:770-778
|
被引
97
次
|
|
|
|
|
16.
Lim B. Enhanced Deep Residual Networks for Single Image Super-Resolution.
Proc of the IEEE Conference on Computer Vision and Pattern Recognition,2017:136-144
|
被引
2
次
|
|
|
|
|
17.
Tai Y. MemNet: A Persistent Memory Network for Image Restoration.
Proc of the IEEE International Conference on Computer Vision,2017:4549-4557
|
被引
6
次
|
|
|
|
|
18.
Choi J S. A Deep Convolutional Neural Network with Selection Units for Super-Resolution.
Proc of the IEEE Conference on Computer Vision and Pattern Recognition,2017:1150-1156
|
被引
1
次
|
|
|
|
|
19.
Li J C. Multi-scale Residual Network for Image Super-Resolution.
Proc of the European Conference on Computer Vision,2018:527-542
|
被引
6
次
|
|
|
|
|
20.
Ahn N. Fast,Accurate,and Lightweight Super-Resolution with Cascading Residual Network.
Proc of the European Conference on Computer Vision,2018:252-268
|
被引
1
次
|
|
|
|
|
了解气象卫星更多信息，请访问