用深度生成先验提升电子菊波成像的抗噪性与效率
Deep generative priors for robust and efficient electron ptychography
- 用卷积神经网络隐式正则化，替代传统手工调参
- 低剂量下信噪比更高，收敛速度加快4倍以上
- 适合材料与生物样本，降低专家依赖
电子菊波成像可实现低剂量原子级分辨率成像，但传统重建算法存在对噪声敏感、收敛慢及需大量人工调参等问题，尤其在三维多层片重建中更为显著。本文提出一种深度生成先验（DGP）框架，利用卷积神经网络的隐式正则化特性解决上述挑战。两个DGP在自动微分的混合态多层片前向模型中分别参数化复数样品和探针。相比基于像素的重建，DGP具备四大优势：(i) 更强的噪声鲁棒性，低剂量下信息极限更高；(ii) 显著更快的收敛速度，尤其在低空间频率下；(iii) 改进的深度方向正则化；(iv) 极少依赖用户指定正则化。DGP框架增强空间一致性并抑制高频噪声，无需复杂调参，预训练策略进一步稳定重建。结果表明，DGP-enabled ptychography是一种鲁棒高效的方法，降低了技术门槛与计算成本，可在多种材料和生物系统中实现高分辨率成像。
原文摘要 · Abstract (English)
Electron ptychography enables dose-efficient atomic-resolution imaging, but conventional reconstruction algorithms suffer from noise sensitivity, slow convergence, and extensive manual hyperparameter tuning for regularization, especially in three-dimensional multislice reconstructions. We introduce a deep generative prior (DGP) framework for electron ptychography that uses the implicit regularization of convolutional neural networks to address these challenges. Two DGPs parameterize the complex-valued sample and probe within an automatic-differentiation mixed-state multislice forward model. Compared to pixel-based reconstructions, DGPs offer four key advantages: (i) greater noise robustness and improved information limits at low dose; (ii) markedly faster convergence, especially at low spatial frequencies; (iii) improved depth regularization; and (iv) minimal user-specified regularization. The DGP framework promotes spatial coherence and suppresses high-frequency noise without extensive tuning, and a pre-training strategy stabilizes reconstructions. Our results establish DGP-enabled ptychography as a robust approach that reduces expertise barriers and computational cost, delivering robust, high-resolution imaging across diverse materials and biological systems.
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。