CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 12566 > Article
Paper
28 March 2023 Reference-based super-resolution with texture transformer and residual network
Ting Liu, YouJia Fu
Author Affiliations +
Proceedings Volume 12566, Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022); 125664C (2023) https://doi.org/10.1117/12.2668143
Event: Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022), 2022, Chongqing, China
Abstract
Due to the large amount of information loss in low-resolution images, it is a challenging task to further develop super-resolution reconstruction techniques for single images. Reference-based super-resolution techniques are considered feasible in recovering high-frequency details of images, etc., but most existing algorithms do not consider the color distribution and illumination distribution of the input image and its reference image. Different, so as not to get very good visual needs. In response to the above problems, we propose a super-resolution model based on texture transfer combined with residual network. By introducing perceptual loss, adversarial loss, reconstruction loss and texture loss to form a new loss function, adjusting the weights of different loss items to optimize the loss function, the ability to reconstruct image details is improved. Extensive experiments show that our proposed model has higher PSNR and SSIM than other methods on the CUFED5, Sun80 and Urban100 test sets.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Citation Download Citation
Ting Liu and YouJia Fu "Reference-based super-resolution with texture transformer and residual network", Proc. SPIE 12566, Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022), 125664C (28 March 2023); https://doi.org/10.1117/12.2668143
ACCESS THE FULL ARTICLE
ORGANIZATIONAL
Sign in with credentials provided by your organization.
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
Members: $17.00
Non-members: $21.00 ADD TO CART
PROCEEDINGS
 6 PAGES
DOWNLOAD PAPER SAVE TO MY LIBRARY
GET CITATION
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Super resolution
Transformers
Image fusion
Feature extraction
Data modeling
Image processing
Technology
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top