Algorithmic unfolding for image reconstruction and localization problems in fluorescence microscopy

We propose an unfolded accelerated projected-gradient descent procedure to estimate model and algorithmic parameters for super-resolution and molecule localization problems in image microscopy. The variational lower-level constraint enforces sparsity of the solution and encodes different noise statistics (Gaussian, Poisson), while the upper-level cost assesses optimality w.r.t. the task considered. In more detail, a standard $\ell_2$ cost is considered for image reconstruction (e.g., deconvolution/superresolution, semi-blind deconvolution) problems, while a smoothed $\ell_1$ loss with learned binarization is employed to assess localization precision in some exemplary fluorescence microscopy problems exploiting single-molecule activation. Several numerical experiments are reported to validate the proposed approach on synthetic and realistic ISBI data.