On neural network methods of image reconstruction and super-resolution

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription or Fee Access

Abstract

The methods for solving the problems of image inpainting and image super-resolution by means of image generation with neural networks are considered. Generative and adversarial neural networks are created and trained to solve them. It is shown that, in a wide range, the recovery quality almost does not depend on the fraction of damaged pixels, that adding residual blocks does not lead to its improvement, and that the generative adversarial network for resolution increase gives better results than the bicubic interpolation.

About the authors

K. A. Rubinov

National Research University "Moscow Power Engineering Institute"

Author for correspondence.
Email: RubinovKA@mpei.ru

аспирант

Russian Federation, Moscow

References

  1. Karras T., Laine S., Aila T. A Style-Based Generator Architecture for Generative Adversarial Networks, arxiv, 2018, available at: https://arxiv.org/abs/1812.04948.
  2. He K., Zhang X., Ren S., Sun J. Deep Residual Learning for Image Recognition, arxiv, 2015, available at: https://arxiv.org/abs/1512.03385.
  3. Foster D. Generative Deep Learning, Sebastopol, California, USA, O’Reilly Media, 2019, 286 p.
  4. Langr J., Bok V. GANs in Action: Deep learning with Generative Adversarial Networks, Shelter Island, New York, USA, Manning Publications, 2019, 278 p.
  5. Goodfellow I. J., Pouget-Abadie J., Mirza M., Xu B., Warde-Farley D., Ozair S., Courville A., Bengio Y. Generative Adversarial Networks, arxiv, 2014, available at: https://arxiv.org/abs/1406.2661.
  6. Radford A., Metz L., Chintala S. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, arxiv, 2016, available at: https://arxiv.org/abs/1511.06434.
  7. Ioffe S., Szeged C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, arxiv, 2015, available at: URL: https://arxiv.org/abs/1502.03167.
  8. Yeh R. A., Chen C., Yian Lim T., Schwing A. G., Hasegawa-Johnson M., Do M. N. Semantic Image Inpainting with Deep Generative Models, arxiv, 2016, available at: https://arxiv.org/abs/1607.07539.
  9. Ledig C., Theis L., Huszar F., Caballero J., Cunningham A., Acosta A., Aitken A., Tejani A., Totz J., Wang Z., Sh W. Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network, arxiv, 2016, available at: https://arxiv.org/abs/1609.04802.
  10. Lim B., Son S., Kim H., Nah S., Mu Lee K. Enhanced Deep Residual Networks for Single Image Super-Resolution, arxiv, 2017, available at: https://arxiv.org/abs/1707.02921.
  11. Simonyan K., Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition, arxiv, 2015, available at: https://arxiv.org/abs/1409.1556.
  12. Huang R., Zhang S., Li T., He R. (2017). Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis, arxiv, 2017, available at: https://arxiv.org/abs/1704.04086.
  13. Celebrities Images, available at: https://www.kaggle.com/greg115/celebrities-100k.
  14. Bulat A., Tzimiropoulos G. How far are we from solving the 2D & 3D Face Alignment problem? (and adataset of 230,000 3D facial landmarks), arxiv, 2017, available at: https://arxiv.org/abs/1703.07332.
  15. Aitken A., Ledig C., Theis L., Caballero J., Wang Z., Shi W. Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize, arxiv, 2017, available at: https://arxiv.org/abs/1707.02937.
  16. Antoniou A., Storkey A., Edwards H. Data Augmentation Generative Adversarial Networks, arxiv, 2017, available at: https://arxiv.org/abs/1711.04340.
  17. Reed S., Akata Z., Yan X., Logeswaran L., Schiele B., Lee H. Generative Adversarial Text to Image Synthesis, arxiv, 2016, available at: https://arxiv.org/abs/1605.05396.
  18. Zhu J. Y., Park T., Isola P., Efros A. A. Unpaired Imageto-Image Translation using Cycle-Consistent Adversarial Networks, arxiv, 2017, available at: https://arxiv.org/abs/1703.10593.
  19. Kim T., Cha M., Kim H., Lee J. K., Kim J. Learning to Discover Cross-Domain Relations with Generative Adversarial Networks, arxiv, 2017, available at: https://arxiv.org/abs/1703.05192.
  20. Yi Z., Zhang H., Tan P., Gong M. DualGAN: Unsupervised Dual Learning for Image-to-Image Translation, arxiv, 2017, available at: https://arxiv.org/abs/1704.02510.
  21. Agustsson E., Timofte R. NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2017, pp. 126—135.
  22. Timofte R., Agustsson E., Gool L. V., Yang M. H., Zhang L., Lim B. and et al. NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2017, pp. 114—125.

Supplementary files

Supplementary Files
Action
1. JATS XML
Download

Copyright (c) 2025 Informacionnye Tehnologii


СМИ зарегистрировано Федеральной службой по надзору в сфере связи, информационных технологий и массовых коммуникаций (Роскомнадзор).
Регистрационный номер и дата принятия решения о регистрации СМИ: серия ПИ № 77 - 15565 от 02 июня 2003 г.