EUVIMEDEUVIMED entdecken
Crossref

Physics-informed two-stage neural network enables computational ghost imaging through unknown scattering media

Zhengqing Gao, Xiaoyan Wu, Xinliang Zhai, Ze Zheng, Jianhong Shi, Jingzheng Huang, Guihua Zeng

Applied Physics Letters · 18.08.2025 · 127 (7)

DOI: 10.1063/5.0283491 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Physics Letters, online erschienen am 18.08.2025. Verfasst von Zhengqing Gao und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 28 Literaturangaben. Gefördert von: Innovation Program for Quantum Science and Technology, Shanghai Municipal Science and Technology Major Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Imaging through scattering media located behind and in front of the object simultaneously remains a significant challenge in computational ghost imaging, as the reconstructed images are often severely degraded due to distorted illumination patterns and attenuated intensity values. In this Letter, we propose an untrained, two-stage self-supervised neural network that effectively mitigates both forward and backward scattering effects. Without the need for any labeled training data, our physics-informed framework exhibits strong adaptability to various types of unknown scattering media. We experimentally demonstrate the robustness of the proposed method by imaging through different scattering environments, including biologically relevant media and rotating ground glass. Compared with the existing reconstruction algorithms, our approach achieves substantially improved image quality for computational ghost imaging in unknown scattering media. This study introduces a paradigm for imaging through complex media and paves the way toward practical applications in biomedical and remote sensing scenarios.

Förderung

  • Innovation Program for Quantum Science and Technology
  • Shanghai Municipal Science and Technology Major Project

Zitieren

APA

Gao, Z., Wu, X., Zhai, X., Zheng, Z., Shi, J., Huang, J., & Zeng, G. (2025). Physics-informed two-stage neural network enables computational ghost imaging through unknown scattering media. Applied Physics Letters, 127(7). https://doi.org/10.1063/5.0283491

Vancouver

Gao Z, Wu X, Zhai X, Zheng Z, Shi J, Huang J, et al. Physics-informed two-stage neural network enables computational ghost imaging through unknown scattering media. Applied Physics Letters. 2025;127(7). doi:10.1063/5.0283491

BibTeX
@article{Gao2025,
  author = {Gao, Zhengqing and Wu, Xiaoyan and Zhai, Xinliang and Zheng, Ze and Shi, Jianhong and Huang, Jingzheng and Zeng, Guihua},
  title = {Physics-informed two-stage neural network enables computational ghost imaging through unknown scattering media},
  journal = {Applied Physics Letters},
  year = {2025},
  volume = {127},
  number = {7},
  doi = {10.1063/5.0283491}
}
Kostenlos starten →