Deep Residual Network in Wavelet Domain for Image Super-resolution
Author:
Affiliation:

Fund Project:

National Key R&D Program of China (2017YFC0803705); National Natural Science Foundation of China (61572004, 61771026); Key Project of Beijing Municipal Education Commission (KZ201910005008); Innovation Platform Construction of Qinghai Province of China (2016-ZJ-Y04)

  • Article
  • | |
  • Metrics
  • |
  • Reference [39]
  • |
  • Related [20]
  • | | |
  • Comments
    Abstract:

    Single Image Super Resolution (SISR) refers to the reconstruction of high resolution images from a low resolution image. Traditional neural network methods typically perform super-resolution reconstruction in the spatial domain of an image, but these methods often ignore important details in the reconstruction process. In view of the fact that wavelet transform can separate the "rough" and "detail" features of image content, this study proposes a wavelet-based deep residual network (DRWSR). Different from other traditional convolutional neural networks, the high-resolution image (HR) is directly derived. This method uses a multi-stage learning strategy to first infer the wavelet coefficients corresponding to the high-resolution image and then reconstruct the super-resolution image (SR). In order to obtain more information, the method uses a flexible and scalable deep neural network with residual nested residuals. In addition, the proposed neural network model is optimized by combining the loss function of image space and wavelet domain. The proposed method is carried out on Set5, Set14, BSD100, Urban100, and other datasets. The experimental results show that the proposed visual effect and peak signal-to-noise ratio (PNSR) are better than the related image super-resolution method.

    Reference
    [1] Glasner D, Bagon S, Irani M. Super-resolution from a single image. In:Proc. of the IEEE Int'l Conf. on Computer Vision. 2009. 349-356.[doi:10.1109/ICCV.2009.5459271]
    [2] Shi W, Caballero J, Ledig C, Zhuang X, Bai W, Bhatia K. Cardiac image super-resolution with global correspondence using multi-atlas PatchMatch. In:Proc. of the 16th Int'l Conf. on Medical Image Computing and Computer-Assisted Intervention-MICCAI 2013. 2013. 9-16.
    [3] Thornton. MW, Atkinson PM, Holland D. Sub-pixel mapping of rural land cover objects from fine spatial resolution satellite sensor imagery using super-resolution pixel-swapping. Int'l Journal of Remote Sensing, 2006,27(3):473-491.[doi:10.1080/01431160500207088]
    [4] Bilgazyev E, Efraty B, Shah SK, Kakadiaris IA. Improved face recognition using super-resolution. In:Proc. of the Int'l Joint Conf. on Biometrics (IJCB). 2011. 1-7.
    [5] Jian M, Lam KM. Simultaneous hallucination and recognition of low-resolution faces based on singular value decomposition. IEEE Trans. on Circuits & Systems for Video Technology, 2015,25(11):1761-1772.[doi:10.1109/TCSVT.2015.2400722]
    [6] Jian M, Lam KM, Dong J. A novel face-hallucination scheme based on singular value decomposition. Pattern Recognition, 2013, 46(11):3091-3102.
    [7] Jian M, Lam KM, Dong J. Facial-feature detection and localization based on a hierarchical scheme. Information Sciences, 2014, 262(3):1-14.
    [8] Jian M, Lam KM. Face-image retrieval based on singular values and potential-field representation. Signal Processing, 2014,100(7):9-15.
    [9] Yang J, Wright J, Huang TS, et al. Image super-resolution via sparse representation. IEEE Trans. on Image Processing, 2010, 19(11):2861-2873.
    [10] Timofte R, Smet VD, Gool LV. A+:Adjusted anchored neighborhood regression for fast super-resolution. In:Proc. of the Asian Conf. on Computer Vision. Springer Int'l Publishing, 2014. 111-126.
    [11] Schulter S, Leistner C, Bischof H. Fast and accurate image upscaling with super-resolution forests. In:Proc. of the Computer Vision and Pattern Recognition. IEEE, 2015. 3791-3799.
    [12] Dong C, Chen CL, He K, Tang X. Image super-resolution using deep convolutional networks. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2016,38(2):295-307.[doi:10.1109/TPAMI.2015.2439281]
    [13] Wang Z, Liu D, Yang J, Han W, Huang T. Deep networks for image super-resolution with sparse prior. In:Proc. of the IEEE Int'l Conf. on Computer Vision. IEEE, 2016. 370-378.
    [14] Kim J, Lee JK, Lee KM. Accurate image super-resolution using very deep convolutional networks. In:Proc. of the Computer Vision and Pattern Recognition. IEEE, 2015. 1646-1654.
    [15] Kim J, Lee JK, Lee KM. Deeply-recursive convolutional network for image super-resolution. In:Proc. of the Computer Vision and Pattern Recognition. IEEE, 2015. 1637-1645.
    [16] Tai Y, Yang J, Liu X. Image super-resolution via deep recursive residual network. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. IEEE Computer Society, 2017. 2790-2798.
    [17] Shi W, Caballero J, Huszar F, Totz J, Aitken AP, Bishop R, Rueckert D, Wang ZH. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In:Proc. of the Computer Vision and Pattern Recognition. IEEE, 2016. 1874-1883.
    [18] Dong C, Chen CL, Tang X. Accelerating the super-resolution convolutional neural network. In:Proc. of the European Conf. on Computer Vision (ECCV). Springer-Verlag, 2016. 391-407.[doi:10.1007/978-3-319-46475-6_25]
    [19] Lai WS. Huang JB. Ahuja N. Yang MH. Deep Laplacian pyramid networks for fast and accurate super-resolution. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2017.
    [20] Mallat S. Wavelets for a vision. Proc. of the IEEE, 1996,84(4):604-614.[doi:10.1109/5.488702]
    [21] Guo T, Mousavi HS, Vu TH, Monga V. Deep wavelet prediction for image super-resolution. In:Proc. of the Computer Vision and Pattern Recognition Workshops. IEEE, 2017. 1100-1109.
    [22] He K, Zhang XY, Ren SH, Sun J. Deep residual learning for image recognition. In:Proc. of the Computer Vision and Pattern Recognition. 2015. 770-778.
    [23] Sun X, Li XG, Li JF, Zhuo L. Review on deep learning based image super-resolution restoration algorithms. Acta Automatica Sinica, 2017,43(5):697-709(in Chinese with English abstract).
    [24] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In:Proc. of the Int'l Conf. on Learning Representations. 2015.
    [25] Johnson J, Alahi A, Li FF. Perceptual losses for real-time style transfer and super-resolution. In:Proc. of the European Conf. on Computer Vision. 2016. 694-711.[doi:10.1007/978-3-319-46475-6_43]
    [26] Ledig C, Theis L, Huszar F, Caballero J, Cunningham A, Acosta A, Aitken A, Tejani A, Totz J, Wang ZH, Shi WZ. Photo-realistic single image super-resolution using a generative adversarial network. In:Proc. of the Computer Vision and Pattern Recognition. 2016. 105-114.
    [27] Wu B, Duan H, Liu Z, Sun GY. SRPGAN:Perceptual generative adversarial network for single image super resolution. In:Proc. of the Computer Vision and Pattern Recognition. 2017.
    [28] El M, Wahed S. Image enhancement using second generation wavelet super resolution. Int'l Journal of Physicalences, 2007,2(6):149-158.
    [29] Ji H. Robust wavelet-based super-resolution reconstruction:Theory and algorithm. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2009,31(4):649-660.[doi:10.1109/TPAMI.2008.103]
    [30] Demirel H, Izadpanahi S, Anbarjafari G. Improved motion-based localized super resolution technique using discrete wavelet transform for low resolution video enhancement. In:Proc. of the IEEE European Conf. on Signal Processing. 2009. 1097-1101.
    [31] Robinson MD, Toth CA, Lo JY, Farsiu S. Efficient Fourier-wavelet super-resolution. IEEE Trans. on Image Processing, 2010, 19(10):2669-2681.[doi:10.1109/TIP.2010.2050107]
    [32] Bevilacqua M, Roumy A, Guillemot C, Alberi-Morel ML. Low-complexity single image super-resolution based on nonnegative neighbor embedding. In:Proc. of the British Machine Vision Conf. 2012.
    [33] Roman Z, Michael E, Matan P. On single image scale-up using sparse-representations. In:Proc. of the Int'l Conf. on Curves and Surfaces. Springer-Verlag, 2012. 711-730.
    [34] Arbelaez P, Maire M, Fowlkes C, Malik J. Contour detection and hierarchical image segmentation. IEEE Trans. on Pattern Analysis & Machine Intelligence, 2011,33(5):898-916.[doi:10.1109/TPAMI.2010.161]
    [35] Huang JB, Singh A, Ahuja N. Single image super-resolution from transformed self-exemplars. In:Proc. of the Computer Vision and Pattern Recognition. IEEE, 2015. 5197-5206.[doi:10.1109/CVPR.2015.7299156]
    [36] Matsui Y, Ito K, Aramaki Y, et al. Sketch-based manga retrieval using Manga109 dataset. Multimedia Tools & Applications, 2017, 76(20):21811-21838.[doi:10.1007/s11042-016-4020-z]
    [37] Lim B, Son SH, Kim HW, Nah SJ, Lee KM. Enhanced deep residual networks for single image super-resolution. In:Proc. of the Computer Vision and Pattern Recognition. 2017.
    附中文参考文献:
    [23] 孙旭,李晓光,李嘉锋,卓力.基于深度学习的图像超分辨复原研究进展.自动化学报,2017,43(5):697-709.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

段立娟,武春丽,恩擎,乔元华,张韵东,陈军成.基于小波域的深度残差网络图像超分辨率算法.软件学报,2019,30(4):941-953

Copy
Share
Article Metrics
  • Abstract:4526
  • PDF: 6388
  • HTML: 3555
  • Cited by: 0
History
  • Received:April 15,2018
  • Revised:June 13,2018
  • Online: April 01,2019
You are the first2032480Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-4
Address:4# South Fourth Street, Zhong Guan Cun, Beijing 100190,Postal Code:100190
Phone:010-62562563 Fax:010-62562533 Email:jos@iscas.ac.cn
Technical Support:Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063