4D-MISR: A unified model for low-dose super-resolution imaging via feature fusion

TL;DR

This paper introduces 4D-MISR, a neural network-based super-resolution technique that fuses multiple low-dose, multi-angle electron microscopy images to achieve atomic-scale visualization of beam-sensitive materials.

Contribution

The paper presents a novel dual-path, attention-guided CNN model for 4D-STEM that enables super-resolution imaging at ultra-low doses, surpassing traditional limits for radiation-sensitive samples.

Findings

Achieves atomic-scale super-resolution from ultra-low-dose data.

Provides comparable spatial resolution to conventional ptychography.

Works effectively on amorphous, semi-crystalline, and crystalline specimens.

Abstract

While electron microscopy offers crucial atomic-resolution insights into structure-property relationships, radiation damage severely limits its use on beam-sensitive materials like proteins and 2D materials. To overcome this challenge, we push beyond the electron dose limits of conventional electron microscopy by adapting principles from multi-image super-resolution (MISR) that have been widely used in remote sensing. Our method fuses multiple low-resolution, sub-pixel-shifted views and enhances the reconstruction with a convolutional neural network (CNN) that integrates features from synthetic, multi-angle observations. We developed a dual-path, attention-guided network for 4D-STEM that achieves atomic-scale super-resolution from ultra-low-dose data. This provides robust atomic-scale visualization across amorphous, semi-crystalline, and crystalline beam-sensitive specimens. Systematic evaluations on representative materials demonstrate comparable spatial resolution to conventional ptychography under ultra-low-dose conditions. Our work expands the capabilities of 4D-STEM, offering a new and generalizable method for the structural analysis of radiation-vulnerable materials.