Fidelity-preserving enhancement of ptychography with foundational text-to-image models

Abstract

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.

References in corpus (12)

• scikit-image: Image processing in Python
• Classifier-Free Diffusion Guidance
• High-Resolution Image Synthesis with Latent Diffusion Models
• SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
• GPT-4o System Card
• DiffEdit: Diffusion-based semantic image editing with mask guidance
• Sigmoid Loss for Language Image Pre-Training
• PtychoDV: Vision Transformer-Based Deep Unrolling Network for Ptychographic Image Reconstruction
• Using a modified double deep image prior for crosstalk mitigation in multislice ptychography
• Zero-shot Image-to-Image Translation
• Pty-Chi: A PyTorch-based modern ptychographic data analysis package
• Plug-and-Play image restoration with Stochastic deNOising REgularization