Journal of Korea Multimedia Society (한국멀티미디어학회논문지)

Korea Multimedia Society (한국멀티미디어학회)
권호 표지
DOI QR코드

DOI QR Code

Fast Very Deep Convolutional Neural Network with Deconvolution for Super-Resolution

Super-Resolution을 위한 Deconvolution 적용 고속 컨볼루션 뉴럴 네트워크

  • Lee, Donghyeon (Inter-university Semiconductor Research Center (ISRC), Department of Electrical Engineering and Computer Science, Seoul National University) ;
  • Lee, Ho Seong (Inter-university Semiconductor Research Center (ISRC), Department of Electrical Engineering and Computer Science, Seoul National University) ;
  • Lee, Kyujoong (Dept. of Electronic Eng., School of Engineering, Sun Moon University) ;
  • Lee, Hyuk-Jae (Inter-university Semiconductor Research Center (ISRC), Department of Electrical Engineering and Computer Science, Seoul National University)
  • Received : 2017.09.22
  • Accepted : 2017.11.03
  • Published : 2017.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

In super-resolution, various methods with Convolutional Neural Network(CNN) have recently been proposed. CNN based methods provide much higher image quality than conventional methods. Especially, VDSR outperforms other CNN based methods in terms of image quality. However, it requires a high computational complexity which prevents real-time processing. In this paper, the method to apply a deconvolution layer to VDSR is proposed to reduce computational complexity. Compared to original VDSR, the proposed method achieves the 4.46 times speed-up and its degradation in image quality is less than -0.1 dB which is negligible.

Keywords

References

  1. D. Glasner, S. Bagon, and M. Irani, "Super-resolution from a Single Image," Proceeding of IEEE 12th International Conference on Computer Vision, pp. 349-356, 2009.
  2. S. Peled and Y. Yeshurun, “Superresolution in MRI: Application to Human White Matter Fiber Tract Visualization By Diffusion Tensor Imaging,” Magnetic Resonance in Medicine, Vol. 45, No. 1, pp. 29-35, 2001. https://doi.org/10.1002/1522-2594(200101)45:1<29::AID-MRM1005>3.0.CO;2-Z
  3. L. Zhang, H. Zhang, H. Shen, and P. Li, “A Super-resolution Reconstruction Algorithm for Surveilance Images,” Signal Processing, Vol. 90, No. 3, pp. 848-859, 2010. https://doi.org/10.1016/j.sigpro.2009.09.002
  4. T. Goto, T. Fukuoka, F. Nagashima, S. Hirano, and M. Sakurai, "Super-resolution System for 4K-HDTV", Proceeding of IEEE 22nd International Conference on Pattern Recognition, pp. 4453-4458, 2014.
  5. H. Chang, D.Y. Yeung, and Y. Xiong, "Super-resolution through Neighbor Embedding," Proceeding of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1, pp. 275-282, 2014.
  6. R. Timofte, V. De Smet, and L. Van Gool, "A+: Adjusted Anchored Neighborhood Regression for Fast Super-resolution," Proceeding of Asian Conference on Computer Vision, pp. 111-126, 2014.
  7. S. Schulter, C. Leistner, and H. Bischof, "Fast and Accurate Image Upscaling with Super-resolution Forests," Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3791-3799, 2015.
  8. W. Shi, J. Caballero, F. Huszar, J. Totz, A.P. Aitken, and R. Bishop, "Real-time Single Image and Video Super-resolution Using an Efficient Sub-pixel Convolutional Neural Network," Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1874-1883, 2016.
  9. C. Dong, C. C. Roy, K. He, and X. Tang, “Image Super-resolution Using Deep Convolutional Networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 38, No. 2, pp. 295-307, 2016. https://doi.org/10.1109/TPAMI.2015.2439281
  10. C. Dong, C.C. Roy, and X. Tang, "Accelerating the Super-resolution Convolutional Neural Network," Proceeding of European Conference on Computer Vision, Springer International Publishing, pp. 391-407, 2016.
  11. J. Kim, J.K. Lee, and K.M. Lee, "Accurate Image Super-resolution Using Very Deep Convolutional Networks," Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1646-1654, 2016.
  12. K. Simonyan and A. Zisserman, "Very Deep Convolutional networks for Large-scale Image Recognition," Proceeding of International Conference on Learning Representations, pp. 40-53, 2015.
  13. 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," Proceedings of the IEEE International Conference on Computer Vision, pp. 416-423, 2001.
  14. M. Bevilacqua, A. Roumy, C. Guillemot and M.L.A. Morel, "Low-complexity Single-image Super-resolution Based on Nonnegative Neighbor Embedding," Proceeding of the 23rd British Machine Vision Conference, pp. 1-10, 2012.
  15. R. Zeyde, M. Elad, and M. Protter, "On Single Image Scale-up Using Sparse-representations," Proceeding of International Conference on Curves and Surfaces, pp. 711-730, 2010.
  16. JB. Huang, A. Singh, and N. Ahuja, "Single Image Super-resolution from Transformed Self-exemplars," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5197-5206, 2015.
  17. A Tensorflow Implementation of "Accurate Image Super-resolution Using Very Deep Convolution Networks," https://github.com/Jongchan/tensorflow-vdsr (Accessed Sep., 21, 2016)
  18. W. Kim, K. Moon, and J. Kim, "Image Enhancement Using Improved Self Degradation Restoration Method," Journal of Korea Multimedia Society, Vol. 16, No. 10, pp. 1180-1188, 2013. https://doi.org/10.9717/kmms.2013.16.10.1180

Cited by

  1. 3D 공간상에서의 주변 기울기 정보를 기반에 둔 필터 학습을 통한 MRI 영상 초해상화 vol.24, pp.2, 2021, https://doi.org/10.9717/kmms.2020.24.2.178