• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

Generative Adversarial Networks for single image with high quality image

Vol. 15, No. 12, December 31, 2021
10.3837/tiis.2021.12.004, Download Paper (Free):

Abstract

The SinGAN is one of generative adversarial networks that can be trained on a single nature image. It has poor ability to learn more global features from nature image, and losses much local detail information when it generates arbitrary size image sample. To solve the problem, a non-linear function is firstly proposed to control downsampling ratio that is ratio between the size of current image and the size of next downsampled image, to increase the ratio with increase of the number of downsampling. This makes the low-resolution images obtained by downsampling have higher proportion in all downsampled images. The low-resolution images usually contain much global information. Therefore, it can help the model to learn more global feature information from downsampled images. Secondly, the attention mechanism is introduced to the generative network to increase the weight of effective image information. This can make the network learn more local details. Besides, in order to make the output image more natural, the TVLoss function is introduced to the loss function of SinGAN, to reduce the difference between adjacent pixels and smear phenomenon for the output image. A large number of experimental results show that our proposed model has better performance than other methods in generating random samples with fixed size and arbitrary size, image harmonization and editing.


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
L. Zhao and Y. Zhang, "Generative Adversarial Networks for single image with high quality image," KSII Transactions on Internet and Information Systems, vol. 15, no. 12, pp. 4326-4344, 2021. DOI: 10.3837/tiis.2021.12.004.

[ACM Style]
Liquan Zhao and Yupeng Zhang. 2021. Generative Adversarial Networks for single image with high quality image. KSII Transactions on Internet and Information Systems, 15, 12, (2021), 4326-4344. DOI: 10.3837/tiis.2021.12.004.

[BibTeX Style]
@article{tiis:25141, title="Generative Adversarial Networks for single image with high quality image", author="Liquan Zhao and Yupeng Zhang and ", journal="KSII Transactions on Internet and Information Systems", DOI={10.3837/tiis.2021.12.004}, volume={15}, number={12}, year="2021", month={December}, pages={4326-4344}}