Awesome MRI Super-Resolution

The definitive, living resource for MRI Super-Resolution research

A comprehensive, actively maintained resource for MRI Super-Resolution covering papers, code, datasets, benchmarks, tutorials, courses, and talks, with a strong focus on MRI-specific challenges informed by advances in computer vision, computational imaging, inverse problems, and MR physics.

Audience: MSc and PhD students, postdoctoral researchers, clinicians (MDs and radiologists), as well as researchers and engineers interested in computational methods for improving MRI image resolution.

Associated Survey (arXiv)

📖 MRI Super-Resolution with Deep Learning: A Comprehensive Survey
Harvard Medical School · University of Eastern Finland

👉 This repository is the official companion to the survey and is designed to be a living extension with continuously updated papers, code, and resources.

📄 Read the survey on arXiv
🤗 Paper on Hugging Face

Disclaimer & Update

This list is not intended to be exhaustive. The items included here highlight key papers, repositories, datasets, open-source tools, tutorials, courses, and talks that we consider most relevant.

This repository is updated quarterly. If we missed a paper, tool, dataset, resource, talk, or course, please open an issue or submit a pull request.

First release: November 20, 2025

Table of Contents

🔗 Select a section below to explore key resources. Click any link to view detailed content.

• Surveys
  

• Papers & Code
  

• Basic Repositories
  

• Datasets
  

• Preprocessing Tools
  

• Quality Assessment Tools
  

• Talks
  

• Tutorials
  

• Courses

Citation

If you find this repository helpful, please consider starring the repo ⭐ and citing our survey paper:

@article{khateri2025mri,
  title={MRI Super-Resolution with Deep Learning: A Comprehensive Survey},
  author={Khateri, Mohammad and Vasylechko, Serge and Ghahremani, Morteza and Timms, Liam and Kocanaogullari, Deniz and Warfield, Simon K and Jaimes, Camilo and Karimi, Davood and Sierra, Alejandra and Tohka, Jussi and Kurugol, Sila and Afacan, Onur},
  journal={arXiv preprint arXiv:2511.16854},
  year={2025}
}