When deep denoising meets iterative phase retrieval
This work addresses noise sensitivity in phase retrieval for applications like lensless imaging, offering a hybrid approach that integrates machine-learned constraints into conventional algorithms.
The paper tackled the problem of recovering signals from Fourier intensity in noisy conditions by combining iterative phase retrieval with deep denoisers, resulting in methods that outperform other noise-robust algorithms.
Recovering a signal from its Fourier intensity underlies many important applications, including lensless imaging and imaging through scattering media. Conventional algorithms for retrieving the phase suffer when noise is present but display global convergence when given clean data. Neural networks have been used to improve algorithm robustness, but efforts to date are sensitive to initial conditions and give inconsistent performance. Here, we combine iterative methods from phase retrieval with image statistics from deep denoisers, via regularization-by-denoising. The resulting methods inherit the advantages of each approach and outperform other noise-robust phase retrieval algorithms. Our work paves the way for hybrid imaging methods that integrate machine-learned constraints in conventional algorithms.