Virtual Talk: High-Speed Fourier Ptychography with Deep Spatio-Temporal Priors
M. Unser
IPAM Long Program on Computational Microscopy, Workshop I: Diffractive Imaging with Phase Retrieval (IPAM-DIPR'22), Virtual, October 10-14, 2022.
Fourier ptychography (FP) involves the acquisition of several low-resolution intensity images of a sample under several illumination angles. These images are then combined into a high-resolution complex-valued image given by the solution to a phase-retrieval problem. Dynamic FP, now, visualizes motion by considering a sequence of such high-resolution images. In this case, the large number of measurements required by standard frame-by-frame reconstruction methods does severely limit the temporal resolution, a drawback that we thwart in this work by proposing a neural-network-based reconstruction framework for dynamic FP. Specifically, we parameterize each image in the desired sequence as the output of a common untrained deep convolutional network driven by series of fixed input vectors that lie on a given one-dimensional (temporal) manifold. We then optimize the parameters of the network to globally fit the acquired measurements with proper time-stamping. The architecture of the network and the constraints on the input vectors impose a spatio-temporal regularization (deep spatio-temporal prior) on the sequence of images. We present numerical experiments that illustrate the ability of our new reconstruction method to achieve a much higher temporal resolution without compromising the spatial resolution.
@INPROCEEDINGS(http://bigwww.epfl.ch/publications/unser2205.html,
AUTHOR="Unser, M.",
TITLE="Virtual Talk: {H}igh-Speed {F}ourier Ptychography with Deep
Spatio-Temporal Priors",
BOOKTITLE="{IPAM} Long Program on Computational Microscopy, Workshop
{I}: {D}iffractive Imaging with Phase Retrieval ({IPAM-DIPR'22})",
YEAR="2022",
editor="",
volume="",
series="",
pages="",
address="Virtual",
month="October 10-14,",
organization="",
publisher="",
note="")