Keywords: Intermediate layer optimization, phase retrieval, generative models
TL;DR: Refined intermediate layer optimization of generative models and new learned initialization schemes perform exceptionally well at the Fourier and Gaussian phase retrieval problem.
Abstract: Fourier phase retrieval is the problem of reconstructing images from magnitude-only measurements. It is relevant in many areas of science, e.g., in X-ray crystallography, astronomy, microscopy, array imaging and optics. When training data is available, generative models can be used to constrain the solution set. However, not all possible solutions are within the range of the generator. Instead, they are represented with some error. To reduce this representation error in the context of phase retrieval, we first leverage a novel variation of intermediate layer optimization (ILO) to extend the range of the generator while still producing images consistent with the training data. Second, we introduce new initialization schemes that further improve the quality of the reconstruction. With extensive experiments, we can show the benefits of our modified ILO and the new initialization schemes.