Improving Multislice Electron Ptychography with a Generative Prior

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Belardi, Christian K., Lee, Chia-Hao, Wang, Yingheng, Lovelace, Justin, Weinberger, Kilian Q., Muller, David A., Gomes, Carla P.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913959576076288
author Belardi, Christian K.
Lee, Chia-Hao
Wang, Yingheng
Lovelace, Justin
Weinberger, Kilian Q.
Muller, David A.
Gomes, Carla P.
author_facet Belardi, Christian K.
Lee, Chia-Hao
Wang, Yingheng
Lovelace, Justin
Weinberger, Kilian Q.
Muller, David A.
Gomes, Carla P.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_17800
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving Multislice Electron Ptychography with a Generative Prior
Belardi, Christian K.
Lee, Chia-Hao
Wang, Yingheng
Lovelace, Justin
Weinberger, Kilian Q.
Muller, David A.
Gomes, Carla P.
Image and Video Processing
Materials Science
Computer Vision and Pattern Recognition
Optics
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.
title Improving Multislice Electron Ptychography with a Generative Prior
topic Image and Video Processing
Materials Science
Computer Vision and Pattern Recognition
Optics
url https://arxiv.org/abs/2507.17800