Optimizing Intermediate Representations of Generative Models for Phase Retrieval

Phase retrieval is the problem of reconstructing images from magnitude-only measurements. In many real-world applications the problem is underdetermined. When training data is available, generative models are a new idea 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 on Fourier and Gaussian phase retrieval problems and thorough ablation studies, we can show the benefits of our modified ILO and the new initialization schemes.