Paper ID: 2412.06806

Ptychoformer: A Physics-Guided Deep Learning Framework for Ptychographic Imaging

Han Yue, Jun Cheng, Yu-Xuan Ren, Philip Heng Wai Leong, Steve Feng Shu

Ptychographic imaging confronts limitations in applying deep learning (DL) for retrieval from diffraction patterns. Conventional neural architectures are optimized for natural images, overlooking the unique physical characteristics of diffraction data, including radial intensity decay and coherent information distributed in concentric rings. In this paper, we present Ptychoformer, a physics-guided DL framework for ptychographic imaging that aligns attention mechanisms and feature extraction with these diffraction physics properties through introducing a dual-branch architecture which accounts for both local and non-local dependencies from the patterns. It consists of a Polar Coordinate Attention (PCA) mechanism that is inspired by the Ewald construction in X-ray crystallography to enhance high-frequency component fidelity. Experimental results demonstrate Ptychoformer's superior performance across both simulated and real data in preserving fine details and suppressing artifacts. On simulated data, Ptychoformer achieves up to 5.4% higher PSNR and 4.2% higher SSIM for amplitude retrieval compared to existing methods. For real experimental data, it demonstrates up to 12.5% higher PSNR and 31.3% higher SSIM for amplitude retrieval. Notably, Ptychoformer maintains robust performance under limited training data and low overlap ratios, outperforming existing models.

Submitted: Nov 25, 2024