A study of unsupervised image super-resolution based on deep network prior

Zhiyuan Zhang; Haoxuan Li

doi:10.1117/12.2635986

5 May 2022 A study of unsupervised image super-resolution based on deep network prior

Zhiyuan Zhang, Haoxuan Li

Proceedings Volume 12245, International Conference on Cryptography, Network Security, and Communication Technology (CNSCT 2022); 122450S (2022) https://doi.org/10.1117/12.2635986
Event: International Conference on Cryptography, Network Security, and Communication Technology (CNSCT 2022), 2022, Sanya, China

Abstract

This research focuses on the topic of image super-resolution based on a deep network prior. This research uses a U-Net-like network structure and modifies the network's hyperparameters, such as the number of downsamples, to find a model with better performance using a control variable approach. Then this best model was applied to different classes of images, and the performance of the network model was investigated by measuring the effect of super-resolution on these classes of images. This research hopes to understand the network structure's role on image super-resolution through such exploratory experiments.

Citation Download Citation

Zhiyuan Zhang and Haoxuan Li "A study of unsupervised image super-resolution based on deep network prior", Proc. SPIE 12245, International Conference on Cryptography, Network Security, and Communication Technology (CNSCT 2022), 122450S (5 May 2022); https://doi.org/10.1117/12.2635986

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