Diffusion Models for Phase Retrieval in Computational Imaging

Phase retrieval refers to the problem of recovering an image from the magnitudes of its complex-valued linear measurements. Since the problem is ill-posed, the recovery requires prior knowledge on the image. We present DOLPH as a deep model-based architecture for phase retrieval that integrates an image prior specified using a diffusion model with a nonconvex data-fidelity term for phase retrieval. Diffusion models are a recent class of deep generative models that are relatively easy to train due to their implementation as image denoisers. DOLPH reconstructs high-quality solutions by alternating data-consistency updates with the sampling step of a diffusion model. Our results show the robustness of DOLPH to noise and its ability to generate several solutions for a given a set of measurements.