Abstract
Traditional super-resolution algorithms are computationally intensive and the quality of generated images is not high. In recent years, due to the superiority of GAN in generating image details, it has begun to attract researchers’ attention. This paper proposes a new GAN-based image super-resolution algorithm, which solves the problems of the current GAN-based super-resolution algorithm that the generated image quality is not high and the multi-scale feature information is not processed enough. In the proposed algorithm, a densely connected dilated convolution network module with different dilation rate is added to enhance the network’s ability to generate image features at different scale levels; a channel attention mechanism is introduced in the network to adaptively select the generated image features, which improves the quality of the generated image on the network. After conducting experiments on classic test datasets, the proposed algorithm has improved PSNR and SSIM compared to ESRGAN.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Li, Xin, Orchard, Michael T.: New edge-directed interpolation. IEEE Trans. Image Process. 10(10), 1521–1527 (2001)
Giachetti, A., Asuni, N.: Real-time artifact-free image upscaling. IEEE Trans. Image Process. A Publ. IEEE Sig. Process. Soc. 20(10), 2760–2768 (2011)
Carey, W.K., Chuang, D.B., Hemami, S.S.: Regularity – preserving image interpolation. IEEE Trans. Image Process. 8(9), 1293–1297 (1999)
Tsai, R., Huang, T.: Advances in Computer Vision and Image Processing, pp. 317–339. JAI Press Inc., Greenwich (1984)
Rhee, S., Kang, M.G.: Discrete cosine transform based regularized high-resolution image reconstruction algorithm. Opt. Eng. 38(8), 1348–1356 (1999)
Nguyen, N., Milanfar, P.: An efficient wavelet-based algorithm for image superresolution. In: Proceedings of the the International Conference on Image Processing, 2000. IEEE (2000)
Dong, C., Loy, C.C., Tang, X.: Accelerating the super-resolution convolutional neural network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision – ECCV 2016. Lecture Notes in Computer Science, vol. 9906, pp. 391–407. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_25
Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., et al.: Generative adversarial networks. Adv. Neural. Inf. Process. Syst. 3, 2672–2680 (2014)
Ledig, C., Theis, L., Huszar, F., et al.: Photo-realistic single image super-resolution using a generative adversarial network (2016)
Wang, X., Yu, K., et al.: Enhanced super-resolution generative adversarial networks. In: European Conference on Computer Vision Workshop, Munich, Germany. 01 09 2018. https://arxiv.org/pdf/1809.00219.pdf
He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition (2015)
Yu, F., Koltun, V., Funkhouser, T.: Dilated residual networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, pp. 636–644 (2017)
Wang, P., Chen, P., Yuan, Y., et al.: Understanding convolution for semantic segmentation. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE (2018)
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. Comput. Sci. (2014)
Kim, J., Lee, J.K., Lee, K.M.: Accurate image super-resolution using very deep convolutional networks (2015)
Tai, Y., Yang, J., Liu, X.: Image super-resolution via deep recursive residual network. In: IEEE Computer Vision and Pattern Recognition. IEEE (2017)
Lim, B., Son, S., Kim, H., et al.: Enhanced deep residual networks for single image super-resolution (2017)
Zhang, Y., Tian, Y., Kong, Y., et al.: Residual dense network for image super-resolution (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Su, K., Li, X., Li, X. (2020). Single Image Super-Resolution Based on Generative Adversarial Networks. In: Wang, Y., Li, X., Peng, Y. (eds) Image and Graphics Technologies and Applications. IGTA 2020. Communications in Computer and Information Science, vol 1314. Springer, Singapore. https://doi.org/10.1007/978-981-33-6033-4_1
Download citation
DOI: https://doi.org/10.1007/978-981-33-6033-4_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-33-6032-7
Online ISBN: 978-981-33-6033-4
eBook Packages: Computer ScienceComputer Science (R0)