ohayonguy/PMRF

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

40
/ 100
Emerging

This project helps anyone working with images to fix blurry, noisy, or low-quality photos. You input a degraded image, and it outputs a significantly clearer, more photo-realistic version. This is ideal for photographers, graphic designers, or content creators who need to enhance the visual quality of existing images without losing important details.

742 stars. No commits in the last 6 months.

Use this if you need to restore or improve the quality of degraded images, especially faces, to achieve a photo-realistic and perceptually pleasing result.

Not ideal if you're looking for a simple, one-click solution without any technical setup or if you only need basic image adjustments like cropping or color correction.

photo-enhancement digital-restoration image-quality visual-content face-enhancement
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

742

Forks

42

Language

Python

License

MIT

Last pushed

Feb 05, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ohayonguy/PMRF"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.