零样本跨材料叠层衍射相位重建的深度学习方法
Zero-Shot Cross-Material Ptychographic Phase Reconstruction Using Deep Learning
浏览论文内容
中文总结 AI 辅助
本文提出一种无需迭代的局部到整体深度学习框架，实现零样本跨材料叠层衍射相位重建，在AuPd和MoS2上迁移性能最佳，速度比ePIE快约10倍。
中文摘要 AI 辅助
叠层衍射相位重建通常被表述为一个迭代逆问题，需要反复进行物体与探针的更新，对于大规模4D-STEM数据会产生巨大的计算成本。我们提出了一种直接的从局部到整体的学习框架，该框架在推理过程中无需迭代细化，即可从衍射测量中重建全场相位图。所提出的网络利用正弦-余弦表示，从单个衍射图案预测局部包裹相位块，并通过校准的扫描位置和高斯加权拼接将这些预测组装成全场重建。为了评估训练域之外的泛化能力，模型在一种材料上训练，并在零样本设置下直接应用于另一种材料，无需目标域微调。在AuPd和MoS2上的实验表明，在两个方向上都存在一致的跨材料迁移，所提出的方法在评估的基于学习的方法中取得了最佳的全场MSE、PSNR和MS-SSIM。与迭代ePIE方法相比，所提出的直接局部到整体流水线将端到端重建时间减少了约10倍，展示了其在高效且可迁移的叠层衍射重建方面的潜力。
英文摘要
Ptychographic phase reconstruction is commonly formulated as an iterative inverse problem, requiring repeated object-probe updates and resulting in substantial computational cost for large-scale 4D-STEM data. We present a direct local-to-global learning framework that reconstructs full-field phase maps from diffraction measurements without iterative refinement during inference. The proposed network predicts local wrapped-phase patches from individual diffraction patterns using a sine-cosine representation, and the predictions are assembled into a full-field reconstruction using calibrated scan positions and Gaussian-weighted stitching. To evaluate generalization beyond the training domain, the model is trained on one material and directly applied to another in a zero-shot setting without target-domain fine-tuning. Experiments on AuPd and MoS$_2$ demonstrate consistent cross-material transfer in both directions, with the proposed method achieving the best full-field MSE, PSNR, and MS-SSIM among the evaluated learning-based methods. Compared with the iterative ePIE approach, the proposed direct local-to-global pipeline reduces end-to-end reconstruction time by approximately 10x, demonstrating its potential for efficient and transferable ptychographic reconstruction.
发表机构
- National Yang Ming Chiao Tung University（国立阳明交通大学）
- National Center for High-performance Computing（国家高速网络与计算中心）
- National Institutes of Applied Research（国家应用研究院）
机构由 AI 辅助整理，请以论文原文为准。
