Robust Compressive Phase Retrieval via Deep Generative Priors
This work addresses phase retrieval for imaging applications, such as through scattering media, but appears incremental as it applies an existing deep generative prior approach to this specific problem.
The paper tackles the ill-posed phase retrieval problem by using deep generative priors with gradient descent, achieving impressive results in terms of measurement efficiency and noise robustness compared to traditional methods like sparsity and denoising frameworks.
This paper proposes a new framework to regularize the highly ill-posed and non-linear phase retrieval problem through deep generative priors using simple gradient descent algorithm. We experimentally show effectiveness of proposed algorithm for random Gaussian measurements (practically relevant in imaging through scattering media) and Fourier friendly measurements (relevant in optical set ups). We demonstrate that proposed approach achieves impressive results when compared with traditional hand engineered priors including sparsity and denoising frameworks for number of measurements and robustness against noise. Finally, we show the effectiveness of the proposed approach on a real transmission matrix dataset in an actual application of multiple scattering media imaging.