Non-Iterative Phase Retrieval With Cascaded Neural Networks
This addresses a limitation in image reconstruction for applications like microscopy or imaging, though it is incremental as it builds on learned methods.
The paper tackles the problem of reconstructing images from non-oversampled Fourier magnitudes in phase retrieval, using a cascaded neural network to achieve improved performance over existing methods on multiple datasets.
Fourier phase retrieval is the problem of reconstructing a signal given only the magnitude of its Fourier transformation. Optimization-based approaches, like the well-established Gerchberg-Saxton or the hybrid input output algorithm, struggle at reconstructing images from magnitudes that are not oversampled. This motivates the application of learned methods, which allow reconstruction from non-oversampled magnitude measurements after a learning phase. In this paper, we want to push the limits of these learned methods by means of a deep neural network cascade that reconstructs the image successively on different resolutions from its non-oversampled Fourier magnitude. We evaluate our method on four different datasets (MNIST, EMNIST, Fashion-MNIST, and KMNIST) and demonstrate that it yields improved performance over other non-iterative methods and optimization-based methods.