CFP last date
20 January 2025
Call for Paper
February Edition
IJCA solicits high quality original research papers for the upcoming February edition of the journal. The last date of research paper submission is 20 January 2025

Submit your paper
Know more
The week's pick
Responsive image
SFLA-Based Line Balancing and Task Optimization in Master-Slave Controlled Hanger Transportation Systems for Garment Production

Duc Hoang Nguyen
Random Articles
Reseach Article

Super-Resolution using Sub-pixel Recursive Adversarial Network with Perceptual Loss

by Ganesh Singh Bisht, Pawan Kumar Mishra
journal cover thumbnail

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 173 - Number 3
Year of Publication: 2017
Authors: Ganesh Singh Bisht, Pawan Kumar Mishra
10.5120/ijca2017915273

Ganesh Singh Bisht, Pawan Kumar Mishra . Super-Resolution using Sub-pixel Recursive Adversarial Network with Perceptual Loss. International Journal of Computer Applications. 173, 3 ( Sep 2017), 28-34. DOI=10.5120/ijca2017915273

@article{ 10.5120/ijca2017915273,
author = { Ganesh Singh Bisht, Pawan Kumar Mishra },
title = { Super-Resolution using Sub-pixel Recursive Adversarial Network with Perceptual Loss },
journal = { International Journal of Computer Applications },
issue_date = { Sep 2017 },
volume = { 173 },
number = { 3 },
month = { Sep },
year = { 2017 },
issn = { 0975-8887 },
pages = { 28-34 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume173/number3/28317-2017915273/ },
doi = { 10.5120/ijca2017915273 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T00:20:17.641321+05:30
%A Ganesh Singh Bisht
%A Pawan Kumar Mishra
%T Super-Resolution using Sub-pixel Recursive Adversarial Network with Perceptual Loss
%J International Journal of Computer Applications
%@ 0975-8887
%V 173
%N 3
%P 28-34
%D 2017
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Super-Resolution is a classic problem in computer vision and many methods have been designed to reconstruct the high-resolution image from low-resolution image. Recent solution of such problem is based on the convolutional neural network where mapping function is used to map low-resolution image to high-resolution image based on per-pixel loss or mean-square error. We introduce a framework that uses perceptual loss function and provides much finer results with high improvement in speed. This framework also replaces the bicubic interpolation for upscaling image with the sub-pixel convolutional layer that learns upscaling filters to upscale the low-resolution feature map to the high-resolution image, that leads less computational complexity. The Proposed method also deals with high upscale factor, by the introduction of an adversarial network that helps in recovering finer texture details in a low-resolution image.

References
  1. D. Glasner, S. Bagon, and M. Irani. 2009. Super-resolution from a single image. International Conference on Computer Vision (ICCV).
  2. Xiong, Z., Sun, X., Wu, F. 2010. Robust web image/video super-resolution. Image Processing, IEEE Transactions on 19(8) 2017–2028.
  3. J. Yang, J. Wright, T. Huang, and Y. Ma. 2010. Image super-resolution via sparse representation. IEEE Transactions on Image Processing, pages 2861–2873.
  4. J. Kim, J. K. Lee, K. M. Lee. 2016. Deeply recursive convolutional network for image super-resolution. Computer Vision and Pattern Recognition.
  5. J. Johnson, A. Alahi, L.F. Fe. 2016. Perceptual Losses for real time style transfer and super-resolution. Computer Vision ECCV.
  6. M. Liang and X. Hu. 2015. Recurrent convolutional neural network for object recognition. CVPR.
  7. S. Borman and R.L. Stevenson. 1998. Super resolution from image sequence – a review. Midwest Symposium on circuits and systems, pages 374-378.
  8. S. Fasiu, M. D. Robinson, M. Elad, and P. Milanfar. 2004. Fast and robust multiframe super resolution. IEEE transaction on image processing. Pages 1327-1344.
  9. Irani, M. Peleg, S. 1991. Improving super-resolution by image registration. Graphical models and image processing, pages 231-239.
  10. Freedman, G. Fattal, R. 2011. Image and video upscaling from local self-examples. ACM Transaction on graphics.
  11. Sun J., Xu Z, Shum H. Y. 2008. Image super-resolution using gradient profile prior. Computer Vision and Pattern Recognition, IEEE.
  12. W.T. Freeman, T.R. Jones, and E.C. Pasztor, O.T. Carmichael. 2000. Learning low level vision. International Journal of Computer Vision, pages 25-27.
  13. W.T. Freeman, T.R. Jones, E.C. Pasztor. 2002. Example based super-resolution. IEEE Computer Graphics and Applications, pages 56-65.
  14. J. B. Huang, A. Singh, and N. Ahuja. 2015. Single image super-resolution from transformed self-exemplars. IEEE Conference on Computer Vision and Pattern Recogniton, pages 5197-5206.
  15. S. Gu, W. Zuo, Q. Xie, D. Meng, X. Feng and L. Zhang. 2015. Convolutional sparse-coding for image super-resolution. IEEE, International conference on computer vision, pages 1823 – 1831.
  16. R. Timofte, V.De Smet, and L. Van Gool. 2013. Anchored neighborhood regression for fast example-based super- resolution. IEEE, International conference on computer vision, pages 1920-1927.
  17. R. Timofte, V. De Smet and L. Van Gool. 2014. A+: Adjusted anchored neighborhood regression for fast super-resolution. Springer, Asian Conference on computer vision, pages 111-126.
  18. H. He and W.C. Siu. 2011. Single image super-resolution using Gaussian process regression. IEEE, conference on computer vision and image processing, pages 449-456.
  19. J. Salvador and E. Perez – Pellitero. 2015. Naive bayes super-resolution forest. International conference on computer vision, pages 325-333.
  20. S. Schulter, C. Leister, and H. Bischof. 2015. Fast and accurate image upscaling with super-resolution forest. IEEE, Conference on computer vision and pattern recognition, pages 3791-3799.
  21. C. Dong, C.C. Loy, K. He and X. Tang. Learning a deep convolutional network for super resolution. Springer, European conference on computer vision. pages 184-199.
  22. C. Dong, C.C. Loy, K. He and X. Tang. 2016. Image super-resolution using deep convolutional networks. IEEE Transactions on pattern analysis and machine learnings, pages 295-307.
  23. Z. Wang, D. Liu, J. Yang. 2015. Deep networks for image super-resolution with sparse-prior. IEEE, International conference on computer vision.
  24. J. Kim, J.K. Lee, and K.M. Lee. 2016. Deeply recursive convolutional networks for image super-resolution. IEEE, Conference on computer vision and pattern recognition.
  25. Simonyan, K. Vedaldi, A. Zisserman A. 2013. Deep inside convolutional networks: visualizing image classifications models and saliency maps. arXiv.
  26. Yosinski J, Clune J., Nguyen A, Fuchs T, Lioson H. 2015. Understanding neural networks with deep visualization. arXiv.
  27. Yang C.Y, Ma C, Yang M.H. 2014. Single-image super resolution: a benchmark. Springer, Computer Vision (ECCV) pages 372-386.
  28. Shan Q, Li Z, Jia J, Tang C.K. 2008. Fast image/video upsampling. ACM Transactions on Graphics.
  29. Kim K.I, Kwon Y. 2010. Single image super-resolution using sparse regression and natural image prior. IEEE transactions on Pattern analysis and machine learning, pages 1127-1133.
  30. Xiong Z, Sun X, Wu F. 2010. Robust web image/video super resolution. IEEE transactions on image processing.
Index Terms

Computer Science
Information Sciences

Keywords

Super-resolution deep learning convolutional neural network perceptual loss adversarial network sub-pixel convolutional layer.

Powered by PhDFocusTM