iamalexkorotin/NeuralOptimalTransport

PyTorch implementation of "Neural Optimal Transport" (ICLR 2023 Spotlight)

41
/ 100
Emerging

This project helps researchers and machine learning practitioners transform images from one style or domain to another without needing paired examples. You input two collections of images (e.g., photos of shoes and photos of handbags), and it outputs new images that visually translate items from the first collection into the style of the second. This is ideal for those working on generative AI and computer vision tasks.

228 stars. No commits in the last 6 months.

Use this if you need to perform high-quality unpaired image-to-image translation and want fine-grained control over the diversity of generated outputs.

Not ideal if you require image translation where exact pixel-level correspondence between input and output is necessary or if you are not comfortable working with Python and Jupyter notebooks.

Image Generation Computer Vision Generative AI Style Transfer Machine Learning Research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

228

Forks

25

Language

Jupyter Notebook

License

MIT

Last pushed

Dec 11, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/iamalexkorotin/NeuralOptimalTransport"

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