Fidelity-preserving enhancement of ptychography with foundational text-to-image models
For researchers in diffraction imaging, this work provides a transferable method to enhance ptychographic reconstructions by leveraging text-guided generative models while preserving physics consistency.
Ptychographic phase retrieval suffers from artifacts like grid pathology and multislice crosstalk. The proposed plug-and-play framework integrates physics-based phase retrieval with text-guided diffusion models, achieving significant artifact suppression and structural fidelity improvements validated by PSNR and diffraction pattern consistency.
Ptychographic phase retrieval enables high-resolution imaging of complex samples but often suffers from artifacts such as grid pathology and multislice crosstalk, which degrade reconstructed images. We propose a plug-and-play (PnP) framework that integrates physics model-based phase retrieval with text-guided image editing using foundational diffusion models. By employing the alternating direction method of multipliers (ADMM), our approach ensures consensus between data fidelity and artifact removal subproblems, maintaining physics consistency while enhancing image quality. Artifact removal is achieved using a text-guided diffusion image editing method (LEDITS++) with a pre-trained foundational diffusion model, allowing users to specify artifacts for removal in natural language. Demonstrations on simulated and experimental datasets show significant improvements in artifact suppression and structural fidelity, validated by metrics such as peak signal-to-noise ratio (PSNR) and diffraction pattern consistency. This work highlights the combination of text-guided generative models and model-based phase retrieval algorithms as a transferable and fidelity-preserving method for high-quality diffraction imaging.