Massively Parallel Spatially-Variant Maximum Likelihood Image Restoration

We consider a massively parallel implementation of Richardson-Lucy or maximum likelihood restoration with a spatially-variant point spread function (PSF). Richardson-Lucy iterates involve the computation of sums of the form: where O(x' q ) is the incident optical field estimate at discrete source location x' q , I(x q ) is the measured discrete image at discrete field location x q , and P(x q , x' q ) is the discrete PSF – the probability that a photon from source region x' q is incident on the detector at field region x q . In general P is a function of source and field coordinates, and the computational burden of Eq. 1 is intractably large.