English

Improving Multislice Electron Ptychography with a Generative Prior

Image and Video Processing 2025-07-28 v2 Materials Science Computer Vision and Pattern Recognition Optics

Abstract

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.

Keywords

Cite

@article{arxiv.2507.17800,
  title  = {Improving Multislice Electron Ptychography with a Generative Prior},
  author = {Christian K. Belardi and Chia-Hao Lee and Yingheng Wang and Justin Lovelace and Kilian Q. Weinberger and David A. Muller and Carla P. Gomes},
  journal= {arXiv preprint arXiv:2507.17800},
  year   = {2025}
}

Comments

16 pages, 10 figures, 5 tables

R2 v1 2026-07-01T04:15:50.775Z