EUVIMEDEUVIMED entdecken
Crossref

Optics-prior-driven network for wavefront sensing with downsampled Shack-Hartmann sensors

Shuwei Yang, Yu Ning, Yulong He, Zixiao Hua, Yu Liu, Jun Li, Wenjing Zhang, Yi Yang, Xiaojun Xu

Optics Express · 01.06.2026 · 34 (11) · 19638

DOI: 10.1364/oe.592048 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Optics Express, online erschienen am 19.05.2026. Verfasst von Shuwei Yang und 8 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Gefördert von: National University of Defense Technology Youth Independent Innovation Science Fund Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Convolutional neural networks (CNNs) have demonstrated significant potential in Shack-Hartmann wavefront sensing by directly recovering phase information from intensity spot patterns. However, the black-box nature of CNNs obscures the physical interpretability of the learned features, thereby limiting model robustness under conditions such as low sampling rates or strong turbulence. To address this, we propose an optics-prior-driven (OPD) framework that explicitly maps CNN-extracted features to physically meaningful spot descriptors, including centroid shifts and spot-shape distortions. Through spatial-response and correlation analyses, we verify that the latent features learned by CNNs correspond directly to these physical parameters. Building on this insight, we develop OPD-Net, which is believed to be a novel network architecture that integrates optical priors into the learning process. The proposed model achieves reconstruction accuracy comparable to conventional CNNs while exhibiting generalization across varying turbulence strengths, microlens-array configurations, and sampling conditions. This study provides the first physics-grounded interpretation of deep learning in Shack-Hartmann wavefront sensing and establishes a robust, interpretable alternative to conventional end-to-end CNN models.

Förderung

  • National University of Defense Technology Youth Independent Innovation Science Fund Project

Zitieren

APA

Yang, S., Ning, Y., He, Y., Hua, Z., Liu, Y., Li, J., Zhang, W., Yang, Y., & Xu, X. (2026). Optics-prior-driven network for wavefront sensing with downsampled Shack-Hartmann sensors. Optics Express, 34(11), 19638. https://doi.org/10.1364/oe.592048

Vancouver

Yang S, Ning Y, He Y, Hua Z, Liu Y, Li J, et al. Optics-prior-driven network for wavefront sensing with downsampled Shack-Hartmann sensors. Optics Express. 2026;34(11):19638. doi:10.1364/oe.592048

BibTeX
@article{Yang2026,
  author = {Yang, Shuwei and Ning, Yu and He, Yulong and Hua, Zixiao and Liu, Yu and Li, Jun and Zhang, Wenjing and Yang, Yi and Xu, Xiaojun},
  title = {Optics-prior-driven network for wavefront sensing with downsampled Shack-Hartmann sensors},
  journal = {Optics Express},
  year = {2026},
  volume = {34},
  number = {11},
  pages = {19638},
  doi = {10.1364/oe.592048}
}
Kostenlos starten →