# Effective Super-Resolution Method for Paired Electron Microscopic Images

## TL;DR

This paper investigates super-resolution techniques specifically for paired electron microscopic images, addressing unique challenges due to the physical differences from optical images and the partial view coverage.

## Contribution

The paper introduces a registration method tailored for electron images and explores training strategies for deep learning super-resolution models, along with a simple non-local-mean alternative.

## Key findings

- Deep learning models require specialized training for electron images.
- The non-local-mean approach performs comparably to deep learning methods.
- Registration of image patches improves super-resolution quality.

## Abstract

This paper is concerned with investigating super-resolution algorithms and solutions for handling electron microscopic images. We note two main aspects differentiating the problem discussed here from those considered in the literature. The first difference is that in the electron imaging setting. We have a pair of physical high-resolution and low-resolution images, rather than a physical image with its downsampled counterpart. The high-resolution image covers about 25% of the view field of the low-resolution image, and the objective is to enhance the area of the low-resolution image where there is no high-resolution counterpart. The second difference is that the physics behind electron imaging is different from that of optical (visible light) photos. The implication is that super-resolution models trained by optical photos are not effective when applied to electron images. Focusing on the unique properties, we devise a global and local registration method to match the high- and low-resolution image patches and explore training strategies for applying deep learning super-resolution methods to the paired electron images. We also present a simple, non-local-mean approach as an alternative. This alternative performs as a close runner-up to the deep learning approaches, but it takes less time to train and entertains a simpler model structure.