让神经网络学会通用解码不同光束的显微图像，提升实时成像能力。
Towards generalizable deep ptychography neural networks
- 用真实探针+生成物体混合训练，聚焦探针学习。
- 单个模型可跨多个光束线重建新实验，效果媲美纯实测数据训练。
- 适合需要实时反馈的高通量科学成像场景。
X射线波前扫描成像是一种数据密集型成像技术，预期将在下一代光源中广泛应用，其相干通量将提升数倍。在加速采集速率下实现实时反馈的需求，推动了深度神经网络等替代重建模型的发展，相比传统方法可实现数量级的速度提升。然而，现有深度学习方法在不同实验条件下缺乏鲁棒性。本文提出一种无监督训练流程，通过结合实验测量的探针与合成的程序化生成物体，强调探针学习。该以探针为中心的方法使单一物理引导神经网络能够重建多个光束线上的未见实验；首次实现了多探针泛化。我们发现探针学习与分布内学习同等重要；使用此合成流程训练的模型，在更换合成训练物体类型时，重建保真度仍可媲美仅使用实验数据训练的模型。该方法支持训练实验调控模型，在动态实验条件下提供实时反馈。
原文摘要 · Abstract (English)
X-ray ptychography is a data-intensive imaging technique expected to become ubiquitous at next-generation light sources delivering many-fold increases in coherent flux. The need for real-time feedback under accelerated acquisition rates motivates surrogate reconstruction models like deep neural networks, which offer orders-of-magnitude speedup over conventional methods. However, existing deep learning approaches lack robustness across diverse experimental conditions. We propose an unsupervised training workflow emphasizing probe learning by combining experimentally-measured probes with synthetic, procedurally generated objects. This probe-centric approach enables a single physics-informed neural network to reconstruct unseen experiments across multiple beamlines; among the first demonstrations of multi-probe generalization. We find probe learning is equally important as in-distribution learning; models trained using this synthetic workflow achieve reconstruction fidelity comparable to those trained exclusively on experimental data, even when changing the type of synthetic training object. The proposed approach enables training of experiment-steering models that provide real-time feedback under dynamic experimental conditions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。