Journal of the Optical Society of America B · 2022 · 10 citations · 31 references
EngineeringBiomedical EngineeringBiomedical ImagingDiagnostic ImagingDigital ImagingImage ProcessingImage ReconstructionImagingInverse ProblemsComputational Complexity Of AlgorithmsHyperparameter OptimizationHyperparameter TuningImage Reconstruction AlgorithmsInverse ImagingInverse Problem FormulationInverse Problem SolvingIterative Reconstruction
Ghost imaging (GI), which employs speckle patterns and bucket signals to reconstruct target images, can be regarded as a typical inverse problem. Iterative algorithms are commonly considered to solve the inverse problem in GI. However, high computational complexity and difficult hyperparameter selection are the bottlenecks. An improved inversion method for GI based on the neural network architecture TransUNet is proposed in this work, called TransUNet-GI. The main idea of this work is to utilize a neural network to avoid issues caused by conventional iterative algorithms in GI. The inversion process is unrolled and implemented on the framework of TransUNet. The demonstrations in simulation and physical experiment show that TransUNet-GI has more promising performance than other methods.
31
Optical imaging by means of two-photon quantum entanglement
T. B. Pittman, Yanhua Shih, Dmitry Strekalov et al. · Physical Review A · 1995 · 2.1K citations
Natural Sciences, Physics, Optics +14
Ori Katz, Yaron Bromberg, Yaron Silberberg · Applied Physics Letters · 2009 · 1K citations · Full text
Two-Photon Imaging with Thermal Light
Alejandra Valencia, Giuliano Scarcelli, Milena D’Angelo et al. · Physical Review Letters · 2005 · 841 citations · Full text
Natural Sciences, Physics, Optics +15
F. Ferri, D. Magatti, L. A. Lugiato et al. · Physical Review Letters · 2010 · 839 citations · Full text