XJTU-XGU/OTCS

Code for "Optimal Transport-Guided Conditional Score-Based Diffusion Model (NeurIPS, 8,7,7,6)"

20
/ 100
Experimental

This project helps generate high-quality images from lower-quality or different styles of images, even when you don't have perfectly matched examples. It takes in collections of images (like low-resolution photos and high-resolution photos, or dog images and cat images) and outputs new images that bridge the gap or improve quality. Image artists, designers, or researchers working with visual data would use this to enhance images or create new visual content.

No commits in the last 6 months.

Use this if you need to perform image super-resolution or image-to-image translation between two different image domains, especially when precise, paired examples are hard to find.

Not ideal if you already have perfectly aligned 'before and after' image pairs for your task, as simpler methods might be more straightforward.

image-generation image-enhancement computer-vision generative-design visual-content-creation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 4 / 25

How are scores calculated?

Stars

67

Forks

2

Language

Jupyter Notebook

License

Last pushed

Dec 11, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/XJTU-XGU/OTCS"

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