Single image super resolution based on generative adversarial networks

Kai Li; Liang Ye; Shenghao Yang; Jinfang Jia; Jianqiang Huang; Xiaoying Wang

doi:10.1117/12.2539692

14 August 2019 Single image super resolution based on generative adversarial networks

Kai Li, Liang Ye, Shenghao Yang, Jinfang Jia, Jianqiang Huang, Xiaoying Wang

Proceedings Volume 11179, Eleventh International Conference on Digital Image Processing (ICDIP 2019); 111790T (2019) https://doi.org/10.1117/12.2539692
Event: Eleventh International Conference on Digital Image Processing (ICDIP 2019), 2019, Guangzhou, China

Abstract

Deep neural networks based on SRGAN single image super-resolution reconstruction can generate more realistic images than CNN-based super-resolution deep neural networks. However, when the network is deeper and more complex, unpleasant artifacts can result. Through a lot of experiments, we can use the ESRGAN model to avoid such problems. When using the ESRGAN model for super-resolution reconstruction, the perceived index of the resulting results does not reach a lower value. There are two reasons for this: (1)ESRGAN does not expand the feature maping. ESRGAN uses 128*128 to obtain the feature information of the image by default, and can't get more image information better. (2) ESRGAN did not re-optimize the generated image. Therefore, we propose ESRGAN-Pro to optimize ESRGAN for the above two aspects, combined with a large amount of training data, and get a better perception index and texture.

Citation Download Citation

Kai Li, Liang Ye, Shenghao Yang, Jinfang Jia, Jianqiang Huang, and Xiaoying Wang "Single image super resolution based on generative adversarial networks", Proc. SPIE 11179, Eleventh International Conference on Digital Image Processing (ICDIP 2019), 111790T (14 August 2019); https://doi.org/10.1117/12.2539692

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available