Home Projects PMRF
PMRF
Python

PMRF

[ICLR 2025] Official implementation of Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration

by ohayonguy · GitHub
Stars
Forks
License
Created
Last commit
Language
blind-face-restorationcolorizationcomputer-visionMITPython
View on GitHub
In plain words

Restore and enhance images to look more realistic using a specialized algorithm for image processing.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
PMRF — GitHub preview card
📈 Star history
753752
2026-07-202026-08-31
📈 Track PMRF

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

[ICLR 2025] Official implementation of Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration

PMRF has 752 stars on GitHub. It has been forked 42 times. PMRF is written mainly in Python. It has been in active development since 2024. PMRF is available under the MIT license. Its main topics are blind-face-restoration, colorization, computer-vision, denoising.

Frequently asked questions

What is PMRF?

[ICLR 2025] Official implementation of Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration

Is PMRF open source?

PMRF is an open-source project. It is released under the MIT license.

Is PMRF free?

Yes. PMRF is free and open source — you can use, modify and self-host it.

What license does PMRF use?

PMRF is available under the MIT license.

What language is PMRF written in?

PMRF is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — PMRF

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=ohayonguy-pmrf)](https://olud.ai/project/ohayonguy-pmrf.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.