Computational ghost imaging for atmospheric turbulence using model-driven and data-driven deep learning

Atmospheric turbulence is a common phenomenon in nature, in which the images obtained are often severely distorted, thus posing a significant challenge to the field of imaging. Computational ghost imaging (CGI), as an indirect imaging modality that exploits second-order correlation algorithms to reconstruct objects, exhibits a strong resistance to turbulence. However, constraints of sampling rate hamper its further application. To address this, data-driven deep learning methods have been proposed, demonstrating superior performance in image reconstruction in low-sampling conditions. While conventional data-driven deep learning approaches demonstrate strong task-specific performance, they are constrained by inherent limitations in generalizability and interpretability. In this paper, we propose a CGI method for atmospheric turbulence that integrates both model-driven and data-driven deep learning techniques. Unlike conventional deep learning methods, our approach combines these two strategies, leveraging the rich implicit features of data-driven methods alongside the generalization and interpretability advantages of model-driven approaches. Simulation and experimental results demonstrate that the proposed method is robust across various sampling ratios and turbulent conditions. Thus, our results provide an effective way for high-quality imaging in atmospheric turbulence.