IVMTRL-SCICVOPTICSJul 23, 2025

Improving Multislice Electron Ptychography with a Generative Prior

CMU
arXiv:2507.17800v23 citationsh-index: 792025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
Originality Incremental advance
AI Analysis

This work addresses reconstruction quality for researchers in materials science and electron microscopy, but it is incremental as it augments existing methods rather than introducing a new paradigm.

The authors tackled the problem of suboptimal and time-consuming reconstructions in multislice electron ptychography by integrating a diffusion model as a generative prior into existing iterative solvers, achieving a 90.50% improvement in SSIM.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes