Image Quality Assessments by Leveraging Diverse Visual Tasks
Image quality assessment (IQA) is a fundamental task in computer vision with the goal of accurately predicting the mean opinion score of humans for assessing the quality of images. While recent advances in deep neural networks (DNNs) have sparked much research on IQA, with the hope for IQA to mimic...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10845170/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832584005237604352 |
|---|---|
| author | Joonhee Lee Dongwon Park Se Young Chun |
| author_facet | Joonhee Lee Dongwon Park Se Young Chun |
| author_sort | Joonhee Lee |
| collection | DOAJ |
| description | Image quality assessment (IQA) is a fundamental task in computer vision with the goal of accurately predicting the mean opinion score of humans for assessing the quality of images. While recent advances in deep neural networks (DNNs) have sparked much research on IQA, with the hope for IQA to mimic humans effectively, there has been a lack of systematic and analytical research on understanding what factors humans prioritize during IQA. This paper aims to identify human priorities in image evaluation by leveraging the DNN models for diverse computer vision tasks and proposes simple, but effective IQA metrics through our comprehensive analyses on those models. Then, these analyses led us to propose a novel vision-ensemble IQA (VE-IQA) method that demonstrated superior performance as compared to prior arts in IQA on popular IQA benchmarks such as LIVE, CSIQ, and TID2013. |
| format | Article |
| id | doaj-art-e899e5e7a7ba4cb5be753cf5f5cea9d6 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-e899e5e7a7ba4cb5be753cf5f5cea9d62025-01-28T00:01:19ZengIEEEIEEE Access2169-35362025-01-0113156391564910.1109/ACCESS.2025.353150010845170Image Quality Assessments by Leveraging Diverse Visual TasksJoonhee Lee0https://orcid.org/0009-0003-6056-4967Dongwon Park1Se Young Chun2https://orcid.org/0000-0001-8739-8960Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of KoreaINMC & IPAI, Seoul National University, Seoul, Republic of KoreaDepartment of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of KoreaImage quality assessment (IQA) is a fundamental task in computer vision with the goal of accurately predicting the mean opinion score of humans for assessing the quality of images. While recent advances in deep neural networks (DNNs) have sparked much research on IQA, with the hope for IQA to mimic humans effectively, there has been a lack of systematic and analytical research on understanding what factors humans prioritize during IQA. This paper aims to identify human priorities in image evaluation by leveraging the DNN models for diverse computer vision tasks and proposes simple, but effective IQA metrics through our comprehensive analyses on those models. Then, these analyses led us to propose a novel vision-ensemble IQA (VE-IQA) method that demonstrated superior performance as compared to prior arts in IQA on popular IQA benchmarks such as LIVE, CSIQ, and TID2013.https://ieeexplore.ieee.org/document/10845170/Image quality assessmentdiverse visual tasksvision-ensemble |
| spellingShingle | Joonhee Lee Dongwon Park Se Young Chun Image Quality Assessments by Leveraging Diverse Visual Tasks IEEE Access Image quality assessment diverse visual tasks vision-ensemble |
| title | Image Quality Assessments by Leveraging Diverse Visual Tasks |
| title_full | Image Quality Assessments by Leveraging Diverse Visual Tasks |
| title_fullStr | Image Quality Assessments by Leveraging Diverse Visual Tasks |
| title_full_unstemmed | Image Quality Assessments by Leveraging Diverse Visual Tasks |
| title_short | Image Quality Assessments by Leveraging Diverse Visual Tasks |
| title_sort | image quality assessments by leveraging diverse visual tasks |
| topic | Image quality assessment diverse visual tasks vision-ensemble |
| url | https://ieeexplore.ieee.org/document/10845170/ |
| work_keys_str_mv | AT joonheelee imagequalityassessmentsbyleveragingdiversevisualtasks AT dongwonpark imagequalityassessmentsbyleveragingdiversevisualtasks AT seyoungchun imagequalityassessmentsbyleveragingdiversevisualtasks |