A Physics-Inspired Deep Learning Framework with Polar Coordinate Attention for Ptychographic Imaging

TL;DR

This paper introduces PPN, a physics-inspired deep learning framework with Polar Coordinate Attention, designed to improve phase retrieval in ptychographic imaging by aligning neural biases with diffraction physics.

Contribution

The paper proposes a novel dual-branch neural network with polar coordinate attention that better models diffraction data, outperforming existing models in ptychographic phase retrieval.

Findings

PPN outperforms existing end-to-end models in preserving high-frequency details.

PPN maintains robust performance at low overlap ratios, suitable for high-throughput imaging.

Spectral and spatial analyses confirm PPN's effectiveness in modeling diffraction physics.

Abstract

Ptychographic imaging confronts inherent challenges in applying deep learning for phase retrieval from diffraction patterns. Conventional neural architectures, both convolutional neural networks and Transformer-based methods, are optimized for natural images with Euclidean spatial neighborhood-based inductive biases that exhibit geometric mismatch with the concentric coherent patterns characteristic of diffraction data in reciprocal space. In this paper, we present PPN, a physics-inspired deep learning network with Polar Coordinate Attention (PoCA) for ptychographic imaging, that aligns neural inductive biases with diffraction physics through a dual-branch architecture separating local feature extraction from non-local coherence modeling. It consists of a PoCA mechanism that replaces Euclidean spatial priors with physically consistent radial-angular correlations. PPN outperforms existing end-to-end models, with spectral and spatial analysis confirming its greater preservation of high-frequency details. Notably, PPN maintains robust performance compared to iterative methods even at low overlap ratios, making it well suited for high-throughput imaging in real-world acquisition scenarios for samples with consistent structural characteristics.