Toward practical phase retrieval with deep learning

Ju Sun
University of Minnesota, Twin Cities

Phase retrieval (PR) concerns the recovery of a signal (1D, 2D, or 3D) from its Fourier magnitudes, and is central to numerous areas of scientific imaging. Over the past decade, there have been numerous breakthroughs in understanding simplified or modified versions of the problem, but the existence of effective and robust methods for the original PR problem remains elusive and so theoretical insights are out of the question. In this talk, I will discuss why PR is difficult, the strengths and limitations of conventional formulations, the promise and perils of deep learning approaches, as well as our recent methods that solve practical PR problems in an unprecedented regime.

Back to Workshop I: Diffractive Imaging with Phase Retrieval