Abstract
In the past few years Single Image Super-Resolution (SISR) has been one of the most researched topics in the field of AI. Super-Resolution Generative Adversarial Nets in short SRGAN paved the way to achieve Super-Resolution (SR) of images while hallucinating a lot of details. Deriving from the main components from SRGAN, i.e. Architecture, Loss and Adversarial nature, we have refined a model that works for very small images, and tries to make out as much information as possible in a short amount of time. The main things being focused are to create a fast Generator which also tries to keep a good SSIM score with the ground truth images, tries to recover as much of the information from relative pixels and also gets close enough to benchmark performance with as limited resources as possible. The core objective of having a simple, fast and light model, is not only to enlarge images but fill in as many missing details as it can from simple pixels, to fully defined and distinct features within that image that might have double or quadruple resolution than the Low-Resolution Images.
P. Sarkar—Co-Author and Supervisor for the Project.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous distributed systems. CoRR abs/1603.04467 (2016). http://arxiv.org/abs/1603.04467
Bevilacqua, M., Roumy, A., Guillemot, C., Alberi-Morel, M.L.: Low-complexity single-image super-resolution based on nonnegative neighbor embedding. In: Proceedings of the British Machine Vision Conference, pp. 135.1–135.10. BMVA Press (2012). https://doi.org/10.5244/C.26.135
Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009)
Dong, C., Loy, C.C., He, K., Tang, X.: Learning a deep convolutional network for image super-resolution. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8692, pp. 184–199. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10593-2_13
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. J. Mach. Learn. Res. Proc. Track 9, 249–256 (2010)
Goodfellow, I.J., et al.: Generative adversarial networks (2014)
Haris, M., Shakhnarovich, G., Ukita, N.: Deep back-projection networks for super-resolution. CoRR abs/1803.02735 (2018). http://arxiv.org/abs/1803.02735
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. CoRR abs/1502.01852 (2015). http://arxiv.org/abs/1502.01852
Huang, G., Liu, Z., Weinberger, K.Q.: Densely connected convolutional networks. CoRR abs/1608.06993 (2016). http://arxiv.org/abs/1608.06993
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. CoRR abs/1502.03167 (2015). http://arxiv.org/abs/1502.03167
Lai, W., Huang, J., Ahuja, N., Yang, M.: Deep Laplacian pyramid networks for fast and accurate super-resolution. CoRR abs/1704.03915 (2017). http://arxiv.org/abs/1704.03915
Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. CoRR abs/1609.04802 (2016). http://arxiv.org/abs/1609.04802
Nene, S.A., Nayar, S.K., Murase, H.: object image library (coil-100. Technical report (1996)
Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. CoRR abs/1609.05158 (2016). http://arxiv.org/abs/1609.05158
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2015)
Tai, Y., Yang, J., Liu, X., Xu, C.: MemNet: a persistent memory network for image restoration. CoRR abs/1708.02209 (2017). http://arxiv.org/abs/1708.02209
Tan, M., Le, Q.V.: EfficientNet: rethinking model scaling for convolutional neural networks. CoRR abs/1905.11946 (2019). http://arxiv.org/abs/1905.11946
Timofte, R., et al.: NTIRE 2018 challenge on single image super-resolution: methods and results. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 965–96511 (2018)
Wang, X., et al.: ESRGAN: enhanced super-resolution generative adversarial networks. CoRR abs/1809.00219 (2018). http://arxiv.org/abs/1809.00219
Wang, Z., Simoncelli, E.P., Bovik, A.C.: Multiscale structural similarity for image quality assessment. In: The Thirty-Seventh Asilomar Conference on Signals, Systems Computers, 2003, vol. 2, pp. 1398–1402 (2003)
Zeyde, R., Elad, M., Protter, M.: On single image scale-up using sparse-representations. In: Boissonnat, J., et al. (eds.) Curves and Surfaces - 7th International Conference, 24–30 June 2010, Avignon, France, Revised Selected Papers. Lecture Notes in Computer Science, vol. 6920, pp. 711–730. Springer (2010). https://doi.org/10.1007/978-3-642-27413-8_47
Zhang, Y., Tian, Y., Kong, Y., Zhong, B., Fu, Y.: Residual dense network for image super-resolution. CoRR abs/1802.08797 (2018). http://arxiv.org/abs/1802.08797
Acknowledgements
We would like to acknowledge Sergey Gladysh for making his batch randomization code available to us. Divakar Devarajan for the transcription of the base paper and Turbasu Chatterjee for the typesetting. Google Colaboratory that was used for early trials. And finally Abhijit Mitra and Paramita Sarkar for guiding us during the culmination of this Paper.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Ghosh, A., Goswami, K., Chatterjee, R., Sarkar, P. (2021). A Light SRGAN for Up-Scaling of Low Resolution and High Latency Images. In: Singh, M., Tyagi, V., Gupta, P.K., Flusser, J., Ören, T., Sonawane, V.R. (eds) Advances in Computing and Data Sciences. ICACDS 2021. Communications in Computer and Information Science, vol 1440. Springer, Cham. https://doi.org/10.1007/978-3-030-81462-5_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-81462-5_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-81461-8
Online ISBN: 978-3-030-81462-5
eBook Packages: Computer ScienceComputer Science (R0)