Full-Reference Image Quality Assessment with Transformer and DISTS

Pei-Fen Tsai, Huai-Nan Peng, Chia-Hung Liao and Shyan-Ming Yuan ()
Additional contact information
Pei-Fen Tsai: Computer Science Department, National Yang Ming Chiao Tung University, No. 1001, Daxue Rd., Est Dist., Hsinchu City 300093, Taiwan
Huai-Nan Peng: Computer Science Department, National Yang Ming Chiao Tung University, No. 1001, Daxue Rd., Est Dist., Hsinchu City 300093, Taiwan
Chia-Hung Liao: Computer Science Department, National Yang Ming Chiao Tung University, No. 1001, Daxue Rd., Est Dist., Hsinchu City 300093, Taiwan
Shyan-Ming Yuan: Computer Science Department, National Yang Ming Chiao Tung University, No. 1001, Daxue Rd., Est Dist., Hsinchu City 300093, Taiwan

Mathematics, 2023, vol. 11, issue 7, 1-15

Abstract: To improve data transmission efficiency, image compression is a commonly used method with the disadvantage of accompanying image distortion. There are many image restoration (IR) algorithms, and one of the most advanced algorithms is the generative adversarial network (GAN)-based method with a high correlation to the human visual system (HVS). To evaluate the performance of GAN-based IR algorithms, we proposed an ensemble image quality assessment (IQA) called ATDIQA (Auxiliary Transformer with DISTS IQA) to give weights on multiscale features global self-attention transformers and local features of convolutional neural network (CNN) IQA of DISTS. The result not only performed better on the perceptual image processing algorithms (PIPAL) dataset with images by GAN IR algorithms but also has good model generalization over LIVE and TID2013 as traditional distorted image datasets. The ATDIQA ensemble successfully demonstrates its performance with a high correlation with the human judgment score of distorted images.

Keywords: image quality assessment (IQA); full-reference IQA; deep image structure and texture similarity (DISTS); transformer IQA; PIPAL dataset; ensemble IQA (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/7/1599/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/7/1599/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:7:p:1599-:d:1107616

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().