Physics-guided topology-aware safeguarded unfolding for low-sampling computational ghost imaging
Optics Express · 02.11.2026 · 34 (22) · 42746
DOI: 10.1364/oe.616758 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Express, online erschienen am 29.10.2026. Verfasst von Mengyi Cao und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical Engineering & Intelligentization, Dongguan University of Technology, Dongguan 523808, Guangdong, China. Die Arbeit nennt 30 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangdong Provincial Key Laboratory of Advanced Particle Detection Technology.
Abstract (Originalsprache)
Low-sampling computational ghost imaging reduces acquisition burden but is highly sensitive to real-system mismatch and structural errors. We propose a physics-guided, topology-aware safeguarded unfolding method for 64 × 64 reconstruction from 300 Cake-Cutting-ordered Hadamard single-exposure measurements (7.3242% sampling). Pattern-wise calibration and physical backprojection establish a real-measurement baseline; topology-error prediction then localizes bounded logit-domain corrections, while residual-aware gating, backtracking, and acceptance criteria constrain multistage updates. On the independent ALL200 real-measurement test set, Dice/clDice/PSNR reach 0.8850/0.8716/16.0130 dB versus 0.8420/0.8691/13.8974 dB for TV-CS, and the mean reconstruction time decreases from 0.1630 s to 0.1206 s. Relative to the physics-adapted U-Net, clDice increases by 0.0417, and the background false-positive rate decreases from 0.0343 to 0.0175.
Autor:innen und Institutionen
- School of Electrical Engineering & Intelligentization, Dongguan University of Technology, Dongguan 523808, Guangdong, China.
- Quantum Science Center of Guangdong-Hong Kong-Macao Greater Bay Area, Shenzhen-Hong Kong International Science and Technology Park, No. 3 Binglang Road, Futian District, Shenzhen 518045, Guangdong, China.
ORCID-Profile: Boyao Li, Jinghua Sun
Förderung
- National Natural Science Foundation of China
- Guangdong Provincial Key Laboratory of Advanced Particle Detection Technology
Zitieren
APA
Cao, M., Duan, W., Li, B., & Sun, J. (2026). Physics-guided topology-aware safeguarded unfolding for low-sampling computational ghost imaging. Optics Express, 34(22), 42746. https://doi.org/10.1364/oe.616758
Vancouver
Cao M, Duan W, Li B, Sun J. Physics-guided topology-aware safeguarded unfolding for low-sampling computational ghost imaging. Optics Express. 2026;34(22):42746. doi:10.1364/oe.616758
BibTeX
@article{Cao2026,
author = {Cao, Mengyi and Duan, Wanqian and Li, Boyao and Sun, Jinghua},
title = {Physics-guided topology-aware safeguarded unfolding for low-sampling computational ghost imaging},
journal = {Optics Express},
year = {2026},
volume = {34},
number = {22},
pages = {42746},
doi = {10.1364/oe.616758}
}
EUVIMED