Improved SRGAN model

Cong Zhu; Fei Wang; Shengping Liang; Keke Liu

doi:10.1117/12.3000809

9 August 2023 Improved SRGAN model

Cong Zhu, Fei Wang, Shengping Liang, Keke Liu

Proceedings Volume 12782, Third International Conference on Image Processing and Intelligent Control (IPIC 2023); 127820F (2023) https://doi.org/10.1117/12.3000809
Event: Third International Conference on Image Processing and Intelligent Control (IPIC 2023), 2023, Kuala Lumpur, Malaysia

Abstract

Image super-resolution reconstruction is an ill-posed problem, as a low-resolution image can correspond to multiple high-resolution images. The models SRCNN and SRDenseNet produce high-resolution images using the mean square error (MSE) loss function, which results in blurry images that are the average of multiple high-quality images. However, the GAN model is capable of reconstructing a more realistic distribution of high-quality images. In this paper, we propose modifications to the SRGAN model by utilizing L1 norm loss for the discriminator's loss function, resulting in a more stable model. We also use VGG16 features for perceptual loss instead of VGG19, which produces better results. The content loss is calculated by weighting both the VGG loss and MSE loss, achieving a better balance between PSNR and human perception.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Cong Zhu, Fei Wang, Shengping Liang, and Keke Liu "Improved SRGAN model", Proc. SPIE 12782, Third International Conference on Image Processing and Intelligent Control (IPIC 2023), 127820F (9 August 2023); https://doi.org/10.1117/12.3000809

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