# Adversarial training with cycle consistency for unsupervised super-resolution in endomicroscopy

arXiv: https://arxiv.org/abs/1901.06988 · HTML: https://mlsanity.com/paper/1901.06988/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jan 2019.

## Built on by (most cited first, 9 of 9)

- [A Comprehensive Review of Deep Learning-based Single Image Super-resolution](https://mlsanity.com/paper/2102.09351/) (2021)
- [Low-field magnetic resonance image enhancement via stochastic image quality transfer](https://mlsanity.com/paper/2304.13385/) (2023)
- [Uncertainty-aware GAN with Adaptive Loss for Robust MRI Image Enhancement](https://mlsanity.com/paper/2110.03343/) (2021)
- [Generating Physically-Consistent Satellite Imagery for Climate Visualizations](https://mlsanity.com/paper/2104.04785/) (2021)
- [A self-supervised and adversarial approach to hyperspectral demosaicking and RGB reconstruction in surgical imaging](https://mlsanity.com/paper/2407.19282/) (2024)
- [An Unsupervised Framework for Joint MRI Super Resolution and Gibbs Artifact Removal](https://mlsanity.com/paper/2302.02849/) (2023)
- [Zero-shot super-resolution with a physically-motivated downsampling kernel for endomicroscopy](https://mlsanity.com/paper/2103.14015/) (2021)
- [Deep Learning in Healthcare: An In-Depth Analysis](https://mlsanity.com/paper/2302.10904/) (2023)
- [Unsupervised Super-Resolution of Satellite Imagery for High Fidelity Material Label Transfer](https://mlsanity.com/paper/2105.07322/) (2021)

## Abstract (arXiv)

In recent years, endomicroscopy has become increasingly used for diagnostic purposes and interventional guidance. It can provide intraoperative aids for real-time tissue characterization and can help to perform visual investigations aimed for example to discover epithelial cancers. Due to physical constraints on the acquisition process, endomicroscopy images, still today have a low number of informative pixels which hampers their quality. Post-processing techniques, such as Super-Resolution (SR), are a potential solution to increase the quality of these images. SR techniques are often supervised, requiring aligned pairs of low-resolution (LR) and high-resolution (HR) images patches to train a model. However, in our domain, the lack of HR images hinders the collection of such pairs and makes supervised training unsuitable. For this reason, we propose an unsupervised SR framework based on an adversarial deep neural network with a physically-inspired cycle consistency, designed to impose some acquisition properties on the super-resolved images. Our framework can exploit HR images, regardless of the domain where they are coming from, to transfer the quality of the HR images to the initial LR images. This property can be particularly useful in all situations where pairs of LR/HR are not available during the training. Our quantitative analysis, validated using a database of 238 endomicroscopy video sequences from 143 patients, shows the ability of the pipeline to produce convincing super-resolved images. A Mean Opinion Score (MOS) study also confirms this quantitative image quality assessment.