Learning to synthesize: robust phase retrieval at low photon counts
Open Access
- 9 March 2020
- journal article
- research article
- Published by Springer Nature in Light: Science & Applications
- Vol. 9 (1) , 1-16
Abstract
The quality of inverse problem solutions obtained through deep learning is limited by the nature of the priors learned from examples presented during the training phase. Particularly in the case of quantitative phase retrieval, spatial frequencies that are underrepresented in the training database, most often at the high band, tend to be suppressed in the reconstruction. Ad hoc solutions have been proposed, such as pre-amplifying the high spatial frequencies in the examples; however, while that strategy improves the resolution, it also leads to high-frequency artefacts, as well as low-frequency distortions in the reconstructions. Here, we present a new approach that learns separately how to handle the two frequency bands, low and high, and learns how to synthesize these two bands into full-band reconstructions. We show that this “learning to synthesize” (LS) method yields phase reconstructions of high spatial resolution and without artefacts and that it is resilient to high-noise conditions, e.g., in the case of very low photon flux. In addition to the problem of quantitative phase retrieval, the LS method is applicable, in principle, to any inverse problem where the forward operator treats different frequency bands unevenly, i.e., is ill-posed.Keywords
All Related Versions
Funding Information
- ODNI | Intelligence Advanced Research Projects Activity (FA8650-17-C-9113, FA8650-17-C-9113, FA8650-17-C-9113, FA8650-17-C-9113, FA8650-17-C-9113)
- Korean Foundation for Advanced Studies scholarship
This publication has 76 references indexed in Scilit:
- Wide-field, high-resolution Fourier ptychographic microscopyNature Photonics, 2013
- $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse RepresentationIEEE Transactions on Signal Processing, 2006
- Decoding by Linear ProgrammingIEEE Transactions on Information Theory, 2005
- An EM algorithm for wavelet-based image restorationIEEE Transactions on Image Processing, 2003
- Thirteen Ways to Look at the Correlation CoefficientThe American Statistician, 1988
- Phase-retrieval stagnation problems and solutionsJournal of the Optical Society of America A, 1986
- Phase imaging by the transport equation of intensityOptics Communications, 1984
- Deterministic phase retrieval: a Green’s function solutionJournal of the Optical Society of America, 1983
- Phase retrieval algorithms: a comparisonApplied Optics, 1982
- Reconstruction of an object from the modulus of its Fourier transformOptics Letters, 1978