SUPER-RESOLUTION USING CONVOLUTIONAL NEURAL NETWORKS WITHOUT ANY CHECKERBOARD ARTIFACTS

被引：0
|
作者：
Sugawara, Yusuke [1 ]
Shiota, Sayaka [1 ]
Kiya, Hitoshi [1 ]
机构：
[1] Tokyo Metropolitan Univ, 6-6 Asahigaoka, Hino, Tokyo, Japan
来源：
2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2018年
关键词：
Super-Resolution; Convolutional Neural Networks; Checkerboard Artifacts; IMAGE SUPERRESOLUTION;
D O I：
暂无
中图分类号：
TP31 [计算机软件];
学科分类号：
081202 ; 0835 ;
摘要：
It is well-known that a number of excellent super-resolution (SR) methods using convolutional neural networks (CNNs) generate checkerboard artifacts. A condition to avoid the checkerboard artifacts is proposed in this paper. So far, checkerboard artifacts have been mainly studied for linear multirate systems, but the condition to avoid checkerboard artifacts can not be applied to CNNs due to the non-linearity of CNNs. We extend the avoiding condition for CNNs, and apply the proposed structure to some typical SR methods to con firm the effectiveness of the new scheme. Experiment results demonstrate that the proposed structure can perfectly avoid to generate checkerboard artifacts under two loss conditions: mean square error and perceptual loss, while keeping excellent properties that the SR methods have.
引用
收藏
页码：66 / 70
页数：5
相关论文
共 50 条
  • [1] Convolutional Neural Networks without Any Checkerboard Artifacts
    Sugawara, Yusuke
    Shiota, Sayaka
    Kiya, Hitoshi
    2018 26TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2018, : 1317 - 1321
  • [2] Super-Resolution Imaging Using Convolutional Neural Networks
    Sun, Yingyi
    Xu, Wenhua
    Zhang, Jie
    Xiong, Jian
    Gui, Guan
    COMMUNICATIONS, SIGNAL PROCESSING, AND SYSTEMS, CSPS 2018, VOL II: SIGNAL PROCESSING, 2020, 516 : 59 - 66
  • [3] 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.
    2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 3944 - 3948
  • [4] SUPER-RESOLUTION OF COMPRESSED VIDEOS USING CONVOLUTIONAL NEURAL NETWORKS
    Kappeler, Armin
    Yoo, Seunghwan
    Dai, Qiqin
    Katsaggelos, Aggelos K.
    2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2016, : 1150 - 1154
  • [5] Super-Resolution PET Imaging Using Convolutional Neural Networks
    Song, Tzu-An
    Chowdhury, Samadrita Roy
    Yang, Fan
    Dutta, Joyita
    IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING, 2020, 6 : 518 - 528
  • [6] Video Super-Resolution With Convolutional Neural Networks
    Kappeler, Armin
    Yoo, Seunghwan
    Dai, Qiqin
    Katsaggelos, Aggelos K.
    IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING, 2016, 2 (02) : 109 - 122
  • [7] Checkerboard artifacts free convolutional neural networks
    Sugawara, Yusuke
    Shiota, Sayaka
    Kiya, Hitoshi
    APSIPA TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING, 2019, 8 : 1 - 9
  • [8] SINGLE DEPTH IMAGE SUPER-RESOLUTION USING CONVOLUTIONAL NEURAL NETWORKS
    Chen, Baoliang
    Jung, Cheolkon
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 1473 - 1477
  • [9] Super-Resolution Convolutional Neural Networks Using Modified and Bilateral ReLU
    Ahn, Hyeongyeom
    Chung, Byungjin
    Yim, Changhoon
    2019 INTERNATIONAL CONFERENCE ON ELECTRONICS, INFORMATION, AND COMMUNICATION (ICEIC), 2019, : 161 - 164
  • [10] IMAGE DEBLURRING AND SUPER-RESOLUTION USING DEEP CONVOLUTIONAL NEURAL NETWORKS
    Albluwi, Fatma
    Krylov, Vladimir A.
    Dahyot, Rozenn
    2018 IEEE 28TH INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), 2018,
12345