Vision Transformers in Image Restoration: A Survey
Sensors · 21.02.2023 · 23 (5) · 2385
DOI: 10.3390/s23052385 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 21.02.2023. Verfasst von Anas M Ali und 5 weiteren Autor:innen. Beteiligte Einrichtung: Robotics and Internet-of-Things Laboratory, Prince Sultan University, Riyadh 12435, Saudi Arabia. Die Arbeit wurde bisher 148-mal zitiert (Crossref) und nennt 146 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: CSRD VA, Prince Sultan University.
Abstract (Originalsprache)
The Vision Transformer (ViT) architecture has been remarkably successful in image restoration. For a while, Convolutional Neural Networks (CNN) predominated in most computer vision tasks. Now, both CNN and ViT are efficient approaches that demonstrate powerful capabilities to restore a better version of an image given in a low-quality format. In this study, the efficiency of ViT in image restoration is studied extensively. The ViT architectures are classified for every task of image restoration. Seven image restoration tasks are considered: Image Super-Resolution, Image Denoising, General Image Enhancement, JPEG Compression Artifact Reduction, Image Deblurring, Removing Adverse Weather Conditions, and Image Dehazing. The outcomes, the advantages, the limitations, and the possible areas for future research are detailed. Overall, it is noted that incorporating ViT in the new architectures for image restoration is becoming a rule. This is due to some advantages compared to CNN, such as better efficiency, especially when more data are fed to the network, robustness in feature extraction, and a better feature learning approach that sees better the variances and characteristics of the input. Nevertheless, some drawbacks exist, such as the need for more data to show the benefits of ViT over CNN, the increased computational cost due to the complexity of the self-attention block, a more challenging training process, and the lack of interpretability. These drawbacks represent the future research direction that should be targeted to increase the efficiency of ViT in the image restoration domain.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Robotics and Internet-of-Things Laboratory, Prince Sultan University, Riyadh 12435, Saudi Arabia.
- Department of Electronics and Electrical Communications Engineering, Faculty of Electronic Engineering, Menoufia University, Menouf 32952, Egypt.
- SE & ICT Laboratory, LR18ES44, ENICarthage, University of Carthage, Tunis 1054, Tunisia.
- Security Engineering Laboratory, Computer Science Department, Prince Sultan University, Riyadh 11586, Saudi Arabia.
- RIADI Laboratory, University of Manouba, Manouba 2010, Tunisia.
ORCID-Profile: Anas M Ali, Bilel Benjdira, Anis Koubaa, Walid El-Shafai, Wadii Boulila
Förderung
- CSRD VA
- Prince Sultan University
Zitieren
APA
Ali, A. M., Benjdira, B., Koubaa, A., El-Shafai, W., Khan, Z., & Boulila, W. (2023). Vision Transformers in Image Restoration: A Survey. Sensors, 23(5), 2385. https://doi.org/10.3390/s23052385
Vancouver
Ali AM, Benjdira B, Koubaa A, El-Shafai W, Khan Z, Boulila W. Vision Transformers in Image Restoration: A Survey. Sensors. 2023;23(5):2385. doi:10.3390/s23052385
BibTeX
@article{Ali2023,
author = {Ali, Anas M and Benjdira, Bilel and Koubaa, Anis and El-Shafai, Walid and Khan, Zahid and Boulila, Wadii},
title = {Vision Transformers in Image Restoration: A Survey},
journal = {Sensors},
year = {2023},
volume = {23},
number = {5},
pages = {2385},
doi = {10.3390/s23052385}
}
EUVIMED