Super-Resolution Imaging Using Convolutional Neural Networks

被引：2
|
作者：
Sun, Yingyi [1 ]
Xu, Wenhua [1 ]
Zhang, Jie [1 ]
Xiong, Jian [1 ]
Gui, Guan [1 ]
机构：
[1] Nanjing Univ Posts & Telecommun, Coll Telecommun & Informat Engn, Nanjing 210003, Peoples R China
来源：
COMMUNICATIONS, SIGNAL PROCESSING, AND SYSTEMS, CSPS 2018, VOL II: SIGNAL PROCESSING | 2020年 / 516卷
关键词：
Super-resolution imaging; Convolutional neural networks; Gradient descent; Adam; RMSprop;
D O I：
10.1007/978-981-13-6504-1_8
中图分类号：
TP31 [计算机软件];
学科分类号：
081202 ; 0835 ;
摘要：
Convolutional neural networks (CNN) have been applied to many classic problems in computer vision. This paper utilized CNNs to reconstruct super-resolution images from low-resolution images. To improve the performance of our model, four optimizations were added in the training process. After comparing the models with these four optimizations, Adam and RMSProp were found to achieve the optimal performance in peak signal to noise ratio (PSNR) and structural similarity index (SSIM). Considering both reconstruction accuracy and training speed, simulation results suggest that RMSProp optimization in the most scenarios.
引用
收藏
页码：59 / 66
页数：8
相关论文
共 50 条
  • [1] Super-Resolution PET Imaging Using Convolutional Neural Networks
    Song, Tzu-An
    Chowdhury, Samadrita Roy
    Yang, Fan
    Dutta, Joyita
    [J]. IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING, 2020, 6 : 518 - 528
  • [2] COMPUTED TOMOGRAPHY SUPER-RESOLUTION USING CONVOLUTIONAL NEURAL NETWORKS
    Yu, Haichao
    Liu, Ding
    Shi, Honghui
    Yu, Hanchao
    Wang, Zhangyang
    Wang, Xinchao
    Cross, Brent
    Bramlet, Matthew
    Huang, Thomas S.
    [J]. 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 3944 - 3948
  • [3] SUPER-RESOLUTION OF COMPRESSED VIDEOS USING CONVOLUTIONAL NEURAL NETWORKS
    Kappeler, Armin
    Yoo, Seunghwan
    Dai, Qiqin
    Katsaggelos, Aggelos K.
    [J]. 2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2016, : 1150 - 1154
  • [4] Video Super-Resolution With Convolutional Neural Networks
    Kappeler, Armin
    Yoo, Seunghwan
    Dai, Qiqin
    Katsaggelos, Aggelos K.
    [J]. IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING, 2016, 2 (02) : 109 - 122
  • [5] SINGLE DEPTH IMAGE SUPER-RESOLUTION USING CONVOLUTIONAL NEURAL NETWORKS
    Chen, Baoliang
    Jung, Cheolkon
    [J]. 2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 1473 - 1477
  • [6] IMAGE DEBLURRING AND SUPER-RESOLUTION USING DEEP CONVOLUTIONAL NEURAL NETWORKS
    Albluwi, Fatma
    Krylov, Vladimir A.
    Dahyot, Rozenn
    [J]. 2018 IEEE 28TH INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), 2018,
  • [7] Super-Resolution Convolutional Neural Networks Using Modified and Bilateral ReLU
    Ahn, Hyeongyeom
    Chung, Byungjin
    Yim, Changhoon
    [J]. 2019 INTERNATIONAL CONFERENCE ON ELECTRONICS, INFORMATION, AND COMMUNICATION (ICEIC), 2019, : 161 - 164
  • [8] Super-Resolution of Color Halftone Images Using Convolutional Neural Networks
    Novaes, Guilherme Apolinario Silva
    Kim, Hae Yong
    [J]. IEEE ACCESS, 2024, 12 : 9082 - 9096
  • [9] Blind Super-Resolution with Deep Convolutional Neural Networks
    Peyrard, Clement
    Baccouche, Moez
    Garcia, Christophe
    [J]. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2016, PT II, 2016, 9887 : 161 - 169
  • [10] Super-Resolution on Degraded Low-Resolution Images Using Convolutional Neural Networks
    Albluwi, Fatma
    Krylov, Vladimir A.
    Dahyot, Rozenn
    [J]. 2019 27TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2019,
12345