I2I-PR: Deep Iterative Refinement for Phase Retrieval using Image-to-Image Diffusion Models
This addresses phase retrieval challenges in fields like imaging and microscopy, representing an incremental advancement through a hybrid approach.
The paper tackles the phase retrieval problem of recovering signals from intensity-only measurements by introducing a novel approach using image-to-image diffusion models with an enhanced initialization stage. The method achieves substantial improvements in training efficiency and reconstruction quality, demonstrating superior results compared to classical and contemporary techniques.
Phase retrieval involves recovering a signal from intensity-only measurements, crucial in many fields such as imaging, holography, optical computing, crystallography, and microscopy. Although there are several well-known phase retrieval algorithms, including classical iterative solvers, the reconstruction performance often remains sensitive to initialization and measurement noise. Recently, image-to-image diffusion models have gained traction in various image reconstruction tasks, yielding significant theoretical insights and practical breakthroughs. In this work, we introduce a novel phase retrieval approach based on an image-to-image diffusion framework called Inversion by Direct Iteration. Our method begins with an enhanced initialization stage that leverages a hybrid iterative technique, combining the Hybrid Input-Output and Error Reduction methods and incorporating a novel acceleration mechanism to obtain a robust crude estimate. Then, it iteratively refines this initial crude estimate using the learned image-to-image pipeline. Our method achieves substantial improvements in both training efficiency and reconstruction quality. Furthermore, our approach utilizes aggregation techniques to refine quality metrics and demonstrates superior results compared to both classical and contemporary techniques. This highlights its potential for effective and efficient phase retrieval across various applications.