MoG-DS: model-guided deep convolutional network for joint denoising and super-resolution of a single-photon counting image

Abstract

Single-photon counting (SPC) imaging has attracted considerable research attention in recent years due to its capability to detect targets under extremely low-light conditions. However, the spatial quality of SPC images is always unsatisfactory because they typically suffer from considerable effects of noise and their spatial resolution is low. Most traditional methods are dedicated to solving the noise problem while ignoring the improvement of spatial resolution. To address these challenging issues, we propose a novel model-guided deep convolutional network for joint denoising and super-resolution (SR) of SPC images. First, we introduce a model-based iterative optimization algorithm with deep regularizer to unify denoising and SR into one problem. Second, we construct a model-guided deep convolutional network by unfolding the aforementioned model-based iterative algorithm to achieve an optimal solution. All modules in the proposed network are interpretable due to the special model-guided design, and they enable good generalization in real situations. In addition, the deep regularizer and other parameters in the proposed network are jointly optimized in an end-to-end manner, which efficiently reduces the difficulty of parameter design. Extensive simulation and real experimental results are reported to demonstrate the superiority of the proposed method in terms of visual comparison and quantitative analysis, respectively.