Pty-Chi: A PyTorch-based modern ptychographic data analysis package

2025-10-23

AI Summary

Existing ptychographic reconstruction software lacks a unified, open-source platform supporting automatic differentiation, modern optimizers, and flexible physical modeling. This work introduces a modular, PyTorch-based reconstruction framework that, for the first time, deeply integrates automatic differentiation into mainstream ptychographic algorithms—including ePIE and DM—enabling GPU acceleration, multi-device parallelization, joint calibration of experimental parameters (e.g., probe relaxation and multi-layer sample modeling), and end-to-end differentiability. The framework is highly extensible, facilitating rapid prototyping of novel physics-informed and data-driven methods. It significantly improves reconstruction accuracy and robustness under challenging conditions such as low coherence, low scan overlap, and illumination instability. Validated at synchrotron facilities, it demonstrates high-resolution, non-destructive imaging capability, providing advanced light source users with an efficient, open computational imaging infrastructure.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Distributed Search

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Ptychography has become an indispensable tool for high-resolution, non-destructive imaging using coherent light sources. The processing of ptychographic data critically depends on robust, efficient, and flexible computational reconstruction software. We introduce Pty-Chi, an open-source ptychographic reconstruction package built on PyTorch that unifies state-of-the-art analytical algorithms with automatic differentiation methods. Pty-Chi provides a comprehensive suite of reconstruction algorithms while supporting advanced experimental parameter corrections such as orthogonal probe relaxation and multislice modeling. Leveraging PyTorch as the computational backend ensures vendor-agnostic GPU acceleration, multi-device parallelization, and seamless access to modern optimizers. An object-oriented, modular design makes Pty-Chi highly extendable, enabling researchers to prototype new imaging models, integrate machine learning approaches, or build entirely new workflows on top of its core components. We demonstrate Pty-Chi's capabilities through challenging case studies that involve limited coherence, low overlap, and unstable illumination during scanning, which highlight its accuracy, versatility, and extensibility. With community-driven development and open contribution, Pty-Chi offers a modern, maintainable platform for advancing computational ptychography and for enabling innovative imaging algorithms at synchrotron facilities and beyond.

Problem

• Developing robust computational software for ptychographic data reconstruction
• Supporting advanced parameter corrections like probe relaxation and multislice modeling
• Enabling flexible prototyping of new imaging models and machine learning integration

Innovation

• PyTorch-based ptychographic reconstruction package
• Unifies analytical algorithms with automatic differentiation
• Modular design enables new imaging models and workflows