milenagazdieva/OT-Super-Resolution

Pytorch implementation of "An Optimal Transport Perspective on Unpaired Image Super-Resolution" (JOTA 2025)

28
/ 100
Experimental

This project offers a method for enhancing the resolution of images when you don't have perfectly matched low and high-resolution pairs. It takes your existing low-resolution images and produces corresponding high-resolution versions, improving visual detail. This is useful for researchers or engineers working with image processing who need to upscale images for various applications.

No commits in the last 6 months.

Use this if you need to upscale images to a higher resolution, especially when you only have unpaired sets of low-resolution and high-resolution examples.

Not ideal if you already have perfectly paired low and high-resolution images for training, or if you need to perform other image-to-image translation tasks beyond super-resolution.

image-super-resolution image-enhancement computer-vision image-processing machine-learning-research
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 6 / 25

How are scores calculated?

Stars

14

Forks

1

Language

Jupyter Notebook

License

MIT

Last pushed

Jul 08, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/milenagazdieva/OT-Super-Resolution"

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