A Physics-Inspired Deep Learning Framework with Polar Coordinate Attention for Ptychographic Imaging
This work addresses the problem of high-throughput ptychographic imaging for researchers in materials science and microscopy, though it is incremental as it adapts existing deep learning concepts to a specific domain.
The paper tackled the challenge of applying deep learning to ptychographic imaging by addressing the geometric mismatch between conventional neural architectures and diffraction patterns, resulting in a model that outperforms existing end-to-end methods with better preservation of high-frequency details and robust performance at low overlap ratios.
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.