Image Quality Assessment: Exploring Joint Degradation Effect of Deep Network Features via Kernel Representation Similarity Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-04 · 47 (4) · 2799-2815
DOI: 10.1109/tpami.2025.3527004 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-04. Verfasst von Xingran Liao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 68 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Chongqing Talent, Joint Equipment Pre Research and Key Fund Project of the Ministry of Education.
Abstract (Originalsprache)
Typically, deep network-based full-reference image quality assessment (FR-IQA) models compare deep features from reference and distorted images pairwise, overlooking correlations among features from the same source. We propose a dual-branch framework to capture the joint degradation effect among deep network features. The first branch uses kernel representation similarity analysis (KRSA), which compares feature self-similarity matrices via the mean absolute error (MAE). The second branch conducts pairwise comparisons via the MAE, and a training-free logarithmic summation of both branches derives the final score. Our approach contributes in three ways. First, integrating the KRSA with pairwise comparisons enhances the model's perceptual awareness. Second, our approach is adaptable to diverse network architectures. Third, our approach can guide perceptual image enhancement. Extensive experiments on 10 datasets validate our method's efficacy, demonstrating that perceptual deformation widely exists in diverse IQA scenarios and that measuring the joint degradation effect can discern appealing content deformations.
Förderung
- National Natural Science Foundation of China
- Chongqing Talent
- Joint Equipment Pre Research and Key Fund Project of the Ministry of Education
- Central University Operating Expenses
- Research Grants Council of the Hong Kong Special Administration Region
Zitieren
APA
Liao, X., Wei, X., Zhou, M., Wong, H. S., & Kwong, S. (2025). Image Quality Assessment: Exploring Joint Degradation Effect of Deep Network Features via Kernel Representation Similarity Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(4), 2799-2815. https://doi.org/10.1109/tpami.2025.3527004
Vancouver
Liao X, Wei X, Zhou M, Wong HS, Kwong S. Image Quality Assessment: Exploring Joint Degradation Effect of Deep Network Features via Kernel Representation Similarity Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(4):2799-2815. doi:10.1109/tpami.2025.3527004
BibTeX
@article{Liao2025,
author = {Liao, Xingran and Wei, Xuekai and Zhou, Mingliang and Wong, Hau-San and Kwong, Sam},
title = {Image Quality Assessment: Exploring Joint Degradation Effect of Deep Network Features via Kernel Representation Similarity Analysis},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {4},
pages = {2799--2815},
doi = {10.1109/tpami.2025.3527004}
}
EUVIMED