用生成模型提升电子显微镜原子结构成像精度
Improving Multislice Electron Ptychography with a Generative Prior
- 用晶体结构数据训练扩散模型，作为重建先验
- 结合迭代算法后，3D重构质量提升90.50%（SSIM）
- 适合需要高精度原子结构重建的研究者
多切片电子全息术（MEP）是一种计算逆成像技术，可从衍射图样重建原子晶体结构的最高分辨率图像。现有算法通常采用迭代求解，但因问题病态而耗时且结果不理想。本文开发了MEP-Diffusion，一种基于大量晶体结构数据训练的扩散模型，专为MEP设计以增强现有迭代求解器。通过扩散后验采样（DPS），MEP-Diffusion可轻松集成至现有重建方法中。该混合方法显著提升了3D重构体积的质量，相比现有方法在结构相似性（SSIM）上提升90.50%。
原文摘要 · Abstract (English)
Multislice electron ptychography (MEP) is an inverse imaging technique that computationally reconstructs the highest-resolution images of atomic crystal structures from diffraction patterns. Available algorithms often solve this inverse problem iteratively but are both time consuming and produce suboptimal solutions due to their ill-posed nature. We develop MEP-Diffusion, a diffusion model trained on a large database of crystal structures specifically for MEP to augment existing iterative solvers. MEP-Diffusion is easily integrated as a generative prior into existing reconstruction methods via Diffusion Posterior Sampling (DPS). We find that this hybrid approach greatly enhances the quality of the reconstructed 3D volumes, achieving a 90.50% improvement in SSIM over existing methods.
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。