EUVIMEDEUVIMED entdecken
Crossref

Blind Image Quality Assessment With Coarse-Grained Perception Construction and Fine-Grained Interaction Learning

Bo Hu, Tuoxun Zhao, Jia Zheng, Yan Zhang, Leida Li, Weisheng Li, Xinbo Gao

IEEE Transactions on Broadcasting · 2024-06 · 70 (2) · 533-544

DOI: 10.1109/tbc.2023.3342696 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Broadcasting, 2024-06. Verfasst von Bo Hu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Chongqing Municipality, Science and Technology Research Program of Chongqing Municipal Education Commission.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image Quality Assessment (IQA) plays an important role in the field of computer vision. However, most of the existing metrics for Blind IQA (BIQA) adopt an end-to-end way and do not adequately simulate the process of human subjective evaluation, which limits further improvements in model performance. In the process of perception, people first give a preliminary impression of the distortion type and relative quality of the images, and then give a specific quality score under the influence of the interaction of the two. Although some methods have attempted to explore the effects of distortion type and relative quality, the relationship between them has been neglected. In this paper, we propose a BIQA with coarse-grained perception construction and fine-grained interaction learning, called PINet for short. The fundamental idea is to learn from the two-stage human perceptual process. Specifically, in the pre-training stage, the backbone initially processes a pair of synthetic distorted images with pseudo-subjective scores, and the multi-scale feature extraction module integrates the deep information and delivers it to the coarse-grained perception construction module, which performs the distortion discrimination and the quality ranking. In the fine-tuning stage, we propose a fine-grained interactive learning module to interact with the two pieces of information to further improve the performance of the proposed PINet. The experimental results prove that the proposed PINet not only achieves competing performances on synthetic distortion datasets but also performs better on authentic distortion datasets.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Chongqing Municipality
  • Science and Technology Research Program of Chongqing Municipal Education Commission
  • Creative Research Groups of Chongqing Municipal Education Commission
  • Chongqing Postdoctoral Research Project Special Support
  • Chongqing Natural Science Foundation Innovation and Development Joint Fund Project
  • Funding of Institute for Advanced Sciences of Chongqing University of Posts and Telecommunications

Zitieren

APA

Hu, B., Zhao, T., Zheng, J., Zhang, Y., Li, L., Li, W., & Gao, X. (2024). Blind Image Quality Assessment With Coarse-Grained Perception Construction and Fine-Grained Interaction Learning. IEEE Transactions on Broadcasting, 70(2), 533-544. https://doi.org/10.1109/tbc.2023.3342696

Vancouver

Hu B, Zhao T, Zheng J, Zhang Y, Li L, Li W, et al. Blind Image Quality Assessment With Coarse-Grained Perception Construction and Fine-Grained Interaction Learning. IEEE Transactions on Broadcasting. 2024;70(2):533-544. doi:10.1109/tbc.2023.3342696

BibTeX
@article{Hu2024,
  author = {Hu, Bo and Zhao, Tuoxun and Zheng, Jia and Zhang, Yan and Li, Leida and Li, Weisheng and Gao, Xinbo},
  title = {Blind Image Quality Assessment With Coarse-Grained Perception Construction and Fine-Grained Interaction Learning},
  journal = {IEEE Transactions on Broadcasting},
  year = {2024},
  volume = {70},
  number = {2},
  pages = {533--544},
  doi = {10.1109/tbc.2023.3342696}
}
Kostenlos starten →