IQA Vision Transformed: A Survey of Transformer Architectures in Perceptual Image Quality Assessment

In an era dominated by visual content, perceptual image quality assessment (IQA) is crucial for enhancing user experiences and driving technological advancements across various domains. This survey paper reviews the integration of Vision Transformers (ViTs) into both no-reference (NR) and full-refer...

Full description

Saved in:
Bibliographic Details
Main Authors: Mobeen Ur Rehman, Imran Fareed Nizami, Farman Ullah, Irfan Hussain
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10767243/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850247133753507840
author Mobeen Ur Rehman
Imran Fareed Nizami
Farman Ullah
Irfan Hussain
author_facet Mobeen Ur Rehman
Imran Fareed Nizami
Farman Ullah
Irfan Hussain
author_sort Mobeen Ur Rehman
collection DOAJ
description In an era dominated by visual content, perceptual image quality assessment (IQA) is crucial for enhancing user experiences and driving technological advancements across various domains. This survey paper reviews the integration of Vision Transformers (ViTs) into both no-reference (NR) and full-reference (FR) IQA methods, highlighting their promise as alternatives to traditional techniques. ViTs leverage attention mechanisms to focus selectively on relevant image patches, showing promise in aligning more closely with human perceptual errors. We identify key limitations of conventional IQA methods and track the evolution from early learning-based approaches to contemporary deep learning models, with a specific focus on ViTs. We discuss the performance of Transformer-based models in capturing image distortions and their strong correlation with subjective IQA metrics. We also discuss potential advancements, including the development of hybrid architectures combining diverse deep learning approaches, adaptive IQA mechanisms through meta-learning, and scalable solutions inspired by emerging computational paradigms. These advancements promise to enhance perceptual quality assessment, with substantial implications for industries such as medical imaging, multimedia applications, and beyond. This study aims to set the groundwork for future research in transformer-based methodologies, offering new insights into the transformative impact of these models on IQA.
format Article
id doaj-art-3dfa2eba4f394756b23e9706a00e1e20
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-3dfa2eba4f394756b23e9706a00e1e202025-08-20T01:59:00ZengIEEEIEEE Access2169-35362024-01-011218336918339310.1109/ACCESS.2024.350627310767243IQA Vision Transformed: A Survey of Transformer Architectures in Perceptual Image Quality AssessmentMobeen Ur Rehman0Imran Fareed Nizami1https://orcid.org/0000-0002-2693-4085Farman Ullah2https://orcid.org/0000-0002-2488-8353Irfan Hussain3Khalifa University Center for Autonomous Robotic Systems (KUCARS), Khalifa University, Abu Dhabi, United Arab EmiratesDepartment of Electrical Engineering, Bahria University, Islamabad, PakistanCollege of Information Technology, United Arab Emirates University, Al Ain, United Arab EmiratesKhalifa University Center for Autonomous Robotic Systems (KUCARS), Khalifa University, Abu Dhabi, United Arab EmiratesIn an era dominated by visual content, perceptual image quality assessment (IQA) is crucial for enhancing user experiences and driving technological advancements across various domains. This survey paper reviews the integration of Vision Transformers (ViTs) into both no-reference (NR) and full-reference (FR) IQA methods, highlighting their promise as alternatives to traditional techniques. ViTs leverage attention mechanisms to focus selectively on relevant image patches, showing promise in aligning more closely with human perceptual errors. We identify key limitations of conventional IQA methods and track the evolution from early learning-based approaches to contemporary deep learning models, with a specific focus on ViTs. We discuss the performance of Transformer-based models in capturing image distortions and their strong correlation with subjective IQA metrics. We also discuss potential advancements, including the development of hybrid architectures combining diverse deep learning approaches, adaptive IQA mechanisms through meta-learning, and scalable solutions inspired by emerging computational paradigms. These advancements promise to enhance perceptual quality assessment, with substantial implications for industries such as medical imaging, multimedia applications, and beyond. This study aims to set the groundwork for future research in transformer-based methodologies, offering new insights into the transformative impact of these models on IQA.https://ieeexplore.ieee.org/document/10767243/Perceptual image quality assessment (IQA)vision transformers (ViTs)transformer architecturesdeep learning for IQAmultimedia applicationscross-domain evaluation
spellingShingle Mobeen Ur Rehman
Imran Fareed Nizami
Farman Ullah
Irfan Hussain
IQA Vision Transformed: A Survey of Transformer Architectures in Perceptual Image Quality Assessment
IEEE Access
Perceptual image quality assessment (IQA)
vision transformers (ViTs)
transformer architectures
deep learning for IQA
multimedia applications
cross-domain evaluation
title IQA Vision Transformed: A Survey of Transformer Architectures in Perceptual Image Quality Assessment
title_full IQA Vision Transformed: A Survey of Transformer Architectures in Perceptual Image Quality Assessment
title_fullStr IQA Vision Transformed: A Survey of Transformer Architectures in Perceptual Image Quality Assessment
title_full_unstemmed IQA Vision Transformed: A Survey of Transformer Architectures in Perceptual Image Quality Assessment
title_short IQA Vision Transformed: A Survey of Transformer Architectures in Perceptual Image Quality Assessment
title_sort iqa vision transformed a survey of transformer architectures in perceptual image quality assessment
topic Perceptual image quality assessment (IQA)
vision transformers (ViTs)
transformer architectures
deep learning for IQA
multimedia applications
cross-domain evaluation
url https://ieeexplore.ieee.org/document/10767243/
work_keys_str_mv AT mobeenurrehman iqavisiontransformedasurveyoftransformerarchitecturesinperceptualimagequalityassessment
AT imranfareednizami iqavisiontransformedasurveyoftransformerarchitecturesinperceptualimagequalityassessment
AT farmanullah iqavisiontransformedasurveyoftransformerarchitecturesinperceptualimagequalityassessment
AT irfanhussain iqavisiontransformedasurveyoftransformerarchitecturesinperceptualimagequalityassessment