We propose a plug-and-play(Pn P) method that uses deep-learning-based denoisers as regularization priors for spectral snapshot compressive imaging(SCI). Our method is efficient in terms of reconstruction quality and s...We propose a plug-and-play(Pn P) method that uses deep-learning-based denoisers as regularization priors for spectral snapshot compressive imaging(SCI). Our method is efficient in terms of reconstruction quality and speed trade-off, and flexible enough to be ready to use for different compressive coding mechanisms. We demonstrate the efficiency and flexibility in both simulations and five different spectral SCI systems and show that the proposed deep Pn P prior could achieve state-of-the-art results with a simple plug-in based on the optimization framework. This paves the way for capturing and recovering multi-or hyperspectral information in one snapshot,which might inspire intriguing applications in remote sensing, biomedical science, and material science. Our code is available at: https://github.com/zsm1211/Pn P-CASSI.展开更多
Ghost imaging(GI)can nonlocally image objects by exploiting the fluctuation characteristics of light fields,where the spatial resolution is determined by the normalized second-order correlation function g^(2) .However...Ghost imaging(GI)can nonlocally image objects by exploiting the fluctuation characteristics of light fields,where the spatial resolution is determined by the normalized second-order correlation function g^(2) .However,the spatial shift-invariant property of g^(2) is distorted when the number of samples is limited,which hinders the deconvolution methods from improving the spatial resolution of GI.In this paper,based on prior imaging systems,we propose a preconditioned deconvolution method to improve the imaging resolution of GI by refining the mutual coherence of a sampling matrix in GI.Our theoretical analysis shows that the preconditioned deconvolution method actually extends the deconvolution technique to GI and regresses into the classical deconvolution technique for the conventional imaging system.The imaging resolution of GI after preconditioning is restricted to the detection noise.Both simulation and experimental results show that the spatial resolution of the reconstructed image is obviously enhanced by using the preconditioned deconvolution method.In the experiment,1.4-fold resolution enhancement over Rayleigh criterion is achieved via the preconditioned deconvolution.Our results extend the deconvolution technique that is only applicable to spatial shift-invariant imaging systems to all linear imaging systems,and will promote their applications in biological imaging and remote sensing for high-resolution imaging demands.展开更多
文摘We propose a plug-and-play(Pn P) method that uses deep-learning-based denoisers as regularization priors for spectral snapshot compressive imaging(SCI). Our method is efficient in terms of reconstruction quality and speed trade-off, and flexible enough to be ready to use for different compressive coding mechanisms. We demonstrate the efficiency and flexibility in both simulations and five different spectral SCI systems and show that the proposed deep Pn P prior could achieve state-of-the-art results with a simple plug-in based on the optimization framework. This paves the way for capturing and recovering multi-or hyperspectral information in one snapshot,which might inspire intriguing applications in remote sensing, biomedical science, and material science. Our code is available at: https://github.com/zsm1211/Pn P-CASSI.
基金National Key Research and Development Program of China(2017YFB0503303)National Natural Science Foundation of China(61991454,11627811,61971146)+1 种基金Shanghai Municipal Science and Technology Major Project(2018SHZDZX01)Open Project of Chinese Academy of Sciences.
文摘Ghost imaging(GI)can nonlocally image objects by exploiting the fluctuation characteristics of light fields,where the spatial resolution is determined by the normalized second-order correlation function g^(2) .However,the spatial shift-invariant property of g^(2) is distorted when the number of samples is limited,which hinders the deconvolution methods from improving the spatial resolution of GI.In this paper,based on prior imaging systems,we propose a preconditioned deconvolution method to improve the imaging resolution of GI by refining the mutual coherence of a sampling matrix in GI.Our theoretical analysis shows that the preconditioned deconvolution method actually extends the deconvolution technique to GI and regresses into the classical deconvolution technique for the conventional imaging system.The imaging resolution of GI after preconditioning is restricted to the detection noise.Both simulation and experimental results show that the spatial resolution of the reconstructed image is obviously enhanced by using the preconditioned deconvolution method.In the experiment,1.4-fold resolution enhancement over Rayleigh criterion is achieved via the preconditioned deconvolution.Our results extend the deconvolution technique that is only applicable to spatial shift-invariant imaging systems to all linear imaging systems,and will promote their applications in biological imaging and remote sensing for high-resolution imaging demands.
