EUVIMEDEUVIMED entdecken
Crossref

PDFormer: a polarization-driven dual-branch transformer for dense fog removal

Qichen Zhang, Tong Zhang, Kaining Yang, Riffat Tehseen, Xue Dong, Pingli Han, Meng Xiang, Fei Liu

Optics Express · 20.04.2026 · 34 (8) · 13950

DOI: 10.1364/oe.589507 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Optics Express, online erschienen am 07.04.2026. Verfasst von Qichen Zhang und 7 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Laboratory of Space Target Awareness, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Foggy scenes pose significant challenges to image restoration due to complex light scattering, which reduces contrast and obscures fine details. Existing defogging methods that rely solely on intensity inputs struggle in dense fog conditions, lacking both physical priors and global reasoning capabilities. A novel dual-branch transformer-based architecture, termed PDFormer, is proposed to integrate physics-based and data-driven insights, aiming to jointly capture global context and recover fine-grained details: the intensity branch employs a hierarchical multiscale window-based Transformer to capture long-range dependencies and structural coherence, while the polarization branch leverages multi-angle polarization images to extract scattering-aware local features guided by physical priors. A lightweight fusion module adaptively integrates both branches, enabling comprehensive restoration across varying fog densities. Extensive experiments on both synthetic and real-world datasets demonstrate that PDFormer achieves state-of-the-art performance in terms of perceptual quality and quantitative metrics, effectively restoring visibility even under challenging atmospheric conditions.

Förderung

  • National Natural Science Foundation of China
  • National Key Laboratory of Space Target Awareness
  • Fundamental Research Funds for the Central Universities
  • Open Research Fund of Beijing Key Laboratory of Advanced Optical Remote Sensing Technology
  • China Postdoctoral Science Foundation
  • Shaanxi Province High-level Innovation and Entrepreneurship Talent Program

Zitieren

APA

Zhang, Q., Zhang, T., Yang, K., Tehseen, R., Dong, X., Han, P., Xiang, M., & Liu, F. (2026). PDFormer: a polarization-driven dual-branch transformer for dense fog removal. Optics Express, 34(8), 13950. https://doi.org/10.1364/oe.589507

Vancouver

Zhang Q, Zhang T, Yang K, Tehseen R, Dong X, Han P, et al. PDFormer: a polarization-driven dual-branch transformer for dense fog removal. Optics Express. 2026;34(8):13950. doi:10.1364/oe.589507

BibTeX
@article{Zhang2026,
  author = {Zhang, Qichen and Zhang, Tong and Yang, Kaining and Tehseen, Riffat and Dong, Xue and Han, Pingli and Xiang, Meng and Liu, Fei},
  title = {PDFormer: a polarization-driven dual-branch transformer for dense fog removal},
  journal = {Optics Express},
  year = {2026},
  volume = {34},
  number = {8},
  pages = {13950},
  doi = {10.1364/oe.589507}
}
Kostenlos starten →