압축된 영상 복원을 위한 양자화된 CNN 기반 초해상화 기법

Quantized CNN-based Super-Resolution Method for Compressed Image Reconstruction

  • 김용우 (상명대학교 시스템반도체공학과) ;
  • 이종환 (상명대학교 시스템반도체공학과)
  • Kim, Yongwoo (Department of System Semiconductor Engineering, Sangmyung University) ;
  • Lee, Jonghwan (Department of System Semiconductor Engineering, Sangmyung University)
  • 투고 : 2020.12.01
  • 심사 : 2020.12.08
  • 발행 : 2020.12.31

초록

In this paper, we propose a super-resolution method that reconstructs compressed low-resolution images into high-resolution images. We propose a CNN model with a small number of parameters, and even if quantization is applied to the proposed model, super-resolution can be implemented without deteriorating the image quality. To further improve the quality of the compressed low-resolution image, a new degradation model was proposed instead of the existing bicubic degradation model. The proposed degradation model is used only in the training process and can be applied by changing only the parameter values to the original CNN model. In the super-resolution image applying the proposed degradation model, visual artifacts caused by image compression were effectively removed. As a result, our proposed method generates higher PSNR values at compressed images and shows better visual quality, compared to conventional CNN-based SR methods.

키워드

참고문헌

  1. E. Perez-Pellitero, J. Salvador, J. Ruiz-Hidalgo, and B. Rosenhahn, "Accelerating super-resolution for 4K upscaling," in Proc. IEEE. Int. Conf. Consum. Electron., Las Vegas, NV, USA, Jan. 2015, pp. 317-320.
  2. Y. Lee and Y.H. Lee, "Implementation of Moving Object Recognition based on Deep Learning," Journal of the Semiconductor & Display Technology, Vol. 17, No. 2, pp.67-70, 2018.
  3. Y. C and Y. C, "A Deep Learning based IOT Device Recognition System," Journal of the Semiconductor & Display Technology, Vol. 18, pp. 1-5, 2019.
  4. C. Dong, C. C. Loy, K. He, and X. Tang, "Learning a deep convolutional network for image super-resolution," Proc. Eur. Conf. Comput. Vis., Zurich, Switzerland, Sep. 2014, pp. 184-199.
  5. C. Dong, C. C. Loy, K. He, and X. Tang, "Image superresolution using deep convolutional networks," IEEE Trans. Pattern Anal. Mach. Intell., vol. 38, no. 2, pp. 295-307, Feb. 2015. https://doi.org/10.1109/TPAMI.2015.2439281
  6. C. Dong, C. C. Loy, and X. Tang, "Accelerating the Super-Resolution Convolutional Neural Network," Part II Proc. European Conf. Computer Vision (ECCV), Springer, LNCS 9906, pp. 391-407, Amsterdam, Netherland, Oct. 8-16, 2016.
  7. A. Aitken, C. Ledig, L. Thesis, J. Caballero, Z. Wang, and W. Shi. (2017). "Checkerboard artifact free subpixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize." [Online]. Available: https://arxiv.org/abs/1707.02937.
  8. J. Kim, J. Kwon. Lee and K. Mu Lee, "Accurate Image Super-Resolution Using Very Deep Convolutional Networks," Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1646 - 1654, Las Vegas, USA, June 27-30, 2016.
  9. K. Simonyan, A. Zisserman. (2015). "Very Deep Convolutional Networks for Large-Scale Image Recognition." [Online]. Available: https://arxiv.org/abs/1409.1556.
  10. W. Shi, J. Caballero, F. Huszar, J. Totz, A. P. Aitken, R. Bishop, D. Rueckert, and Z. Wang, "Real-time single image and video super-resolution using an efficient subpixel convolutional neural network," Proc. IEEE Conf. Comput. Vision and Pattern Recog. (CVPR), Las Vegas, USA, June 27-30, 2016, pp. 1874-1883.
  11. B. Lim, S. Son, H. Kim, S. Nah, and K. Mu Lee, "Enhanced Deep Residual Networks for Single Image Super-Resolution," Proc. IEEE Conf. Comput. Vision and Pattern Recog. Workshops, Hawaii, USA, July 21- 26, 2017, pp. 1132-1140.
  12. Kai Zhang, Wangmeng Zuo, and Lei Zhang, "Learning a single convolutional super-resolution network for multiple degradations," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 3262-3271.
  13. Y. Kim, J. Choi and M. Kim, "A Real-Time Convolutional Neural Network for Super-Resolution on FPGA With Applications to 4K UHD 60 fps Video Services," in IEEE Transactions on Circuits and Systems for Video Technology, vol. 29, no. 8, pp. 2521-2534, Aug. 2019. https://doi.org/10.1109/TCSVT.2018.2864321
  14. M. Shabany, "Floating-point to Fixed-point conversion." [Online]. Available: http://ee.sharif.edu/-digitalvlsi/Docs/Fixed-Point.pdf.
  15. S. Gupta, A. Agrawal, K. Gopalakrishnan, and P. Narayanan. (2015). "Deep Learning with Limited Numerical Precision." [Online]. Available: https://arxiv.org/abs/1502.02551.
  16. D. Martin, C. Fowlkes, D. Tal, and J. Malik, "A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics," Proc. 8th IEEE Int. Conf. Comput. Vis., vol. 2. Jul. 2001, pp. 416-423.
  17. J. Yang, J. Wright, T. S. Huang, and Y. Ma, "Image super-resolution via sparse representation," IEEE Trans. Image Process., vol. 19, no. 11, pp. 2861-2873, Nov. 2010. https://doi.org/10.1109/TIP.2010.2050625
  18. M. Bevilacqua et al., "Low-complexity single-image super-resolution based on nonnegative neighbor embedding," Proc. 23rd Brit. Mach. Vis. Conf. (BMVC), Guildford, U.K., Sep. 2012, pp. 135.1-135.10.
  19. R. Zeyde, M. Elad, and M. Protter, "On single image scale-up using sparse-representations," Proc. 7th Int. Conf. Curves Surf., Jun. 2010, pp. 711-730.
  20. J.-B. Huang, A. Singh, and N. Ahuja, "Single image super-resolution from transformed self-exemplars," Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Boston, MA, USA, Jun. 2015, pp. 5197-5206.