Lens-less imaging via score-based generative model

Abstract：Lens-less imaging is affected by twinning noise occurring in in-line holograms，and the recon• structed results continuously face poor reconstruction signal-to-noise ratio and low imaging resolution.This study proposes a lens-less imaging via a score-based generation model.In the training phase，the pro• posed model perturbs data distribution by gradually adding Gaussian noise by using a continuous stochastic differential equation (SDE).A continuous time-dependent score-based function with denoising score matching is then trained and used to solve the inverse SDE required to generate object sample data.In the testing phase，a single Fresnel zone aperture is used as a mask to achieve lens-less encoding modulation un• der incoherent illumination.The prediction-correction method is then used to alternate iteration steps be• tween the numerical SDE solver and data-fidelity term to achieve lens-less imaging reconstruction.Valida• tion results on LSUN-bedroom and LSUN-church datasets show that the proposed algorithm can effective• ly eliminate twin image noise，and the peak signal-to-noise ratio(PSNR)and structural similarity(SSIM) of the reconstruction results can reach 25. 23 dB and 0. 65，respectively.The PSNR values of the recon• struction results are 17.49 dB and 7. 16 dB，which is higher than that of lens-less imaging algorithms