DOI QR코드

DOI QR Code

SDCN: Synchronized Depthwise Separable Convolutional Neural Network for Single Image Super-Resolution

  • 투고 : 2021.11.05
  • 발행 : 2021.11.30

초록

Recently, image super-resolution techniques used in convolutional neural networks (CNN) have led to remarkable performance in the research area of digital image processing applications and computer vision tasks. Convolutional layers stacked on top of each other can design a more complex network architecture, but they also use more memory in terms of the number of parameters and introduce the vanishing gradient problem during training. Furthermore, earlier approaches of single image super-resolution used interpolation technique as a pre-processing stage to upscale the low-resolution image into HR image. The design of these approaches is simple, but not effective and insert the newer unwanted pixels (noises) in the reconstructed HR image. In this paper, authors are propose a novel single image super-resolution architecture based on synchronized depthwise separable convolution with Dense Skip Connection Block (DSCB). In addition, unlike existing SR methods that only rely on single path, but our proposed method used the synchronizes path for generating the SISR image. Extensive quantitative and qualitative experiments show that our method (SDCN) achieves promising improvements than other state-of-the-art methods.

키워드

참고문헌

  1. Freeman, W.T., E.C. Pasztor, and O.T. Carmichael, Learning low-level vision. International journal of computer vision, 2000. 40(1): p. 25-47. https://doi.org/10.1023/A:1026501619075
  2. Shamsolmoali, P., et al., Deep convolution network for surveillance records super-resolution. Multimedia Tools and Applications, 2019. 78(17): p. 23815-23829. https://doi.org/10.1007/s11042-018-5915-7
  3. Isaac, J.S. and R. Kulkarni. Super resolution techniques for medical image processing. in 2015 International Conference on Technologies for Sustainable Development (ICTSD). 2015. IEEE.
  4. Yang, X., et al., Long-distance object recognition with image super resolution: A comparative study. IEEE Access, 2018. 6: p. 13429-13438. https://doi.org/10.1109/access.2018.2799861
  5. Unser, M., A. Aldroubi, and M. Eden, Fast B-spline transforms for continuous image representation and interpolation. IEEE Transactions on pattern analysis and machine intelligence, 1991. 13(3): p. 277-285. https://doi.org/10.1109/34.75515
  6. Li, X. and M.T. Orchard, New edge-directed interpolation. IEEE transactions on image processing, 2001. 10(10): p. 1521-1527. https://doi.org/10.1109/83.951537
  7. Duchon, C.E., Lanczos filtering in one and two dimensions. Journal of Applied Meteorology and Climatology, 1979. 18(8): p. 1016-1022. https://doi.org/10.1175/1520-0450(1979)018<1016:LFIOAT>2.0.CO;2
  8. Marquina, A. and S.J. Osher, Image super-resolution by TV-regularization and Bregman iteration. Journal of Scientific Computing, 2008. 37(3): p. 367-382. https://doi.org/10.1007/s10915-008-9214-8
  9. Sun, J., Z. Xu, and H.-Y. Shum. Image super-resolution using gradient profile prior. in 2008 IEEE Conference on Computer Vision and Pattern Recognition. 2008. IEEE.
  10. Tai, Y.-W., et al. Super resolution using edge prior and single image detail synthesis. in 2010 IEEE computer society conference on computer vision and pattern recognition. 2010. IEEE.
  11. Stark, H. and P. Oskoui, High-resolution image recovery from image-plane arrays, using convex projections. JOSA A, 1989. 6(11): p. 1715-1726. https://doi.org/10.1364/JOSAA.6.001715
  12. Schultz, R.R. and R.L. Stevenson, Extraction of high-resolution frames from video sequences. IEEE transactions on image processing, 1996. 5(6): p. 996-1011. https://doi.org/10.1109/83.503915
  13. Schultz, R.R. and R.L. Stevenson. Improved definition video frame enhancement. in 1995 International Conference on Acoustics, Speech, and Signal Processing. 1995. IEEE.
  14. Jia, K., X. Wang, and X. Tang, Image transformation based on learning dictionaries across image spaces. IEEE transactions on pattern analysis and machine intelligence, 2012. 35(2): p. 367-380. https://doi.org/10.1109/TPAMI.2012.95
  15. Bevilacqua, M., et al., Low-complexity single-image super-resolution based on nonnegative neighbor embedding. 2012.
  16. Freeman, W.T., T.R. Jones, and E.C. Pasztor, Example-based super-resolution. IEEE Computer graphics and Applications, 2002. 22(2): p. 56-65. https://doi.org/10.1109/38.988747
  17. Chang, H., D.-Y. Yeung, and Y. Xiong. Super-resolution through neighbor embedding. in Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004. 2004. IEEE.
  18. Dong, C., et al. Learning a deep convolutional network for image super-resolution. in European conference on computer vision. 2014. Springer.
  19. Shi, W., et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
  20. Kim, J., J.K. Lee, and K.M. Lee. Accurate image super-resolution using very deep convolutional networks. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
  21. Dong, C., C.C. Loy, and X. Tang. Accelerating the super-resolution convolutional neural network. in European conference on computer vision. 2016. Springer.
  22. Kim, J., J.K. Lee, and K.M. Lee. Deeply-recursive convolutional network for image super-resolution. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
  23. Lai, W.-S., et al. Deep laplacian pyramid networks for fast and accurate super-resolution. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
  24. He, K., et al. Deep residual learning for image recognition. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
  25. Lim, B., et al. Enhanced deep residual networks for single image super-resolution. in Proceedings of the IEEE conference on computer vision and pattern recognition workshops. 2017.
  26. Ahn, N., B. Kang, and K.-A. Sohn. Fast, accurate, and lightweight super-resolution with cascading residual network. in Proceedings of the European Conference on Computer Vision (ECCV). 2018.
  27. Chollet, F. Xception: Deep Learning with Depthwise Separable Convolutions. in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017.
  28. Szegedy, C., et al. Going deeper with convolutions. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.
  29. Ioffe, S. and C. Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. in International conference on machine learning. 2015. PMLR.
  30. Zhang, Y., et al. Residual dense network for image super-resolution. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2018.
  31. Fan, Y., et al. Balanced two-stage residual networks for image super-resolution. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2017.
  32. Timofte, R., V. De Smet, and L. Van Gool. A+: Adjusted anchored neighborhood regression for fast super-resolution. in Asian conference on computer vision. 2014. Springer.
  33. Schulter, S., C. Leistner, and H. Bischof. Fast and accurate image upscaling with super-resolution forests. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.