Image Quality Assessment: Measuring Perceptual Degradation via Distribution Measures in Deep Feature Spaces
IEEE Transactions on Image Processing · 2024 · 33 · 4044-4059
DOI: 10.1109/tip.2024.3409176 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2024. Verfasst von Xingran Liao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 41-mal zitiert (Crossref) und nennt 67 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Hong Kong General Research Fund-Research Grant Council (GRFRGC) GRF, Chongqing Talent.
Abstract (Originalsprache)
This study aims to develop advanced and training-free full-reference image quality assessment (FR-IQA) models based on deep neural networks. Specifically, we investigate measures that allow us to perceptually compare deep network features and reveal their underlying factors. We find that distribution measures enjoy advanced perceptual awareness and test the Wasserstein distance (WSD), Jensen-Shannon divergence (JSD), and symmetric Kullback-Leibler divergence (SKLD) measures when comparing deep features acquired from various pretrained deep networks, including the Visual Geometry Group (VGG) network, SqueezeNet, MobileNet, and EfficientNet. The proposed FR-IQA models exhibit superior alignment with subjective human evaluations across diverse image quality assessment (IQA) datasets without training, demonstrating the advanced perceptual relevance of distribution measures when comparing deep network features. Additionally, we explore the applicability of deep distribution measures in image super-resolution enhancement tasks, highlighting their potential for guiding perceptual enhancements. The code is available on website. (https://github.com/Buka-Xing/Deep-network-based-distribution-measures-for-full-reference-image-quality-assessment).
Förderung
- National Natural Science Foundation of China
- Hong Kong General Research Fund-Research Grant Council (GRFRGC) GRF
- Chongqing Talent
Zitieren
APA
Liao, X., Wei, X., Zhou, M., Li, Z., & Kwong, S. (2024). Image Quality Assessment: Measuring Perceptual Degradation via Distribution Measures in Deep Feature Spaces. IEEE Transactions on Image Processing, 33, 4044-4059. https://doi.org/10.1109/tip.2024.3409176
Vancouver
Liao X, Wei X, Zhou M, Li Z, Kwong S. Image Quality Assessment: Measuring Perceptual Degradation via Distribution Measures in Deep Feature Spaces. IEEE Transactions on Image Processing. 2024;33:4044-4059. doi:10.1109/tip.2024.3409176
BibTeX
@article{Liao2024,
author = {Liao, Xingran and Wei, Xuekai and Zhou, Mingliang and Li, Zhengguo and Kwong, Sam},
title = {Image Quality Assessment: Measuring Perceptual Degradation via Distribution Measures in Deep Feature Spaces},
journal = {IEEE Transactions on Image Processing},
year = {2024},
volume = {33},
pages = {4044--4059},
doi = {10.1109/tip.2024.3409176}
}
EUVIMED