Deep Super-Resolution Network for Single Image Super-Resolution with Realistic Degradations

被引:1
|
作者
Umer, Rao Muhammad [1 ]
Foresti, Gian Luca [1 ]
Micheloni, Christian [1 ]
机构
[1] Univ Udine, Udine, Italy
关键词
super-resolution; convolutional neural network; realistic degradations; computational efficient;
D O I
10.1145/3349801.3349823
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Single Image Super-Resolution (SISR) aims to generate a high-resolution (HR) image of a given low-resolution (LR) image. The most of existing convolutional neural network (CNN) based SISR methods usually take an assumption that a LR image is only bicubicly down-sampled version of an HR image. However, the true degradation (i.e. the LR image is a bicubicly downsampled, blurred and noisy version of an HR image) of a LR image goes beyond the widely used bicubic assumption, which makes the SISR problem highly ill-posed nature of inverse problems. To address this issue, we propose a deep SISR network that works for blur kernels of different sizes, and different noise levels in an unified residual CNN-based denoiser network, which significantly improves a practical CNN-based super-resolver for real applications. Extensive experimental results on synthetic LR datasets and real images demonstrate that our proposed method not only can produce better results on more realistic degradation but also computational efficient to practical SISR applications.
引用
收藏
页数:7
相关论文
共 50 条
  • [1] Deep Residual Network for Single Image Super-Resolution
    Wang, Haimin
    Liao, Kai
    Yan, Bin
    Ye, Run
    [J]. ICCCV 2019: PROCEEDINGS OF THE 2ND INTERNATIONAL CONFERENCE ON CONTROL AND COMPUTER VISION, 2019, : 66 - 70
  • [2] Generative adversarial image super-resolution network for multiple degradations
    Lin, Hong
    Fan, Jing
    Zhang, Yangyi
    Peng, Dewei
    [J]. IET IMAGE PROCESSING, 2020, 14 (17) : 4520 - 4527
  • [3] Deep Network Cascade for Image Super-resolution
    Cui, Zhen
    Chang, Hong
    Shan, Shiguang
    Zhong, Bineng
    Chen, Xilin
    [J]. COMPUTER VISION - ECCV 2014, PT V, 2014, 8693 : 49 - 64
  • [4] Deep Unfolding Network for Image Super-Resolution
    Zhang, Kai
    Van Gool, Luc
    Timofte, Radu
    [J]. 2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, : 3214 - 3223
  • [5] Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
    Zhang, Kai
    Zuo, Wangmeng
    Zhang, Lei
    [J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 3262 - 3271
  • [6] A Compact Deep Neural Network for Single Image Super-Resolution
    Xu, Xiaoyu
    Qian, Jian
    Yu, Li
    Yu, Shengju
    HaoTao
    Zhu, Ran
    [J]. MULTIMEDIA MODELING (MMM 2020), PT II, 2020, 11962 : 148 - 160
  • [7] Deep coordinate attention network for single image super-resolution
    Xie, Chao
    Zhu, Hongyu
    Fei, Yeqi
    [J]. IET IMAGE PROCESSING, 2022, 16 (01) : 273 - 284
  • [8] Adaptive deep residual network for single image super-resolution
    Liu, Shuai
    Gang, Ruipeng
    Li, Chenghua
    Song, Ruixia
    [J]. COMPUTATIONAL VISUAL MEDIA, 2019, 5 (04) : 391 - 401
  • [9] Adaptive deep residual network for single image super-resolution
    Shuai Liu
    Ruipeng Gang
    Chenghua Li
    Ruixia Song
    [J]. Computational Visual Media, 2019, 5 (04) : 391 - 401
  • [10] Adaptive deep residual network for single image super-resolution
    Shuai Liu
    Ruipeng Gang
    Chenghua Li
    Ruixia Song
    [J]. Computational Visual Media, 2019, 5 : 391 - 401