iamalexkorotin/KernelNeuralOptimalTransport

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

29
/ 100
Experimental

This project helps researchers and machine learning practitioners perform image-to-image translation between different visual domains, even when there are no paired examples. It takes images from one category (like female faces) and transforms them into another (like anime characters), or between objects like handbags and shoes, outputting new, translated images. This tool is designed for those working on advanced computer vision tasks involving generative models and image synthesis.

No commits in the last 6 months.

Use this if you need to translate images from one visual domain to another, especially when you require precise control over the diversity of the generated outputs and better interpretability of the transformation process.

Not ideal if your primary goal is basic image manipulation or if you don't require the advanced mathematical properties of optimal transport for your image generation tasks.

image-to-image-translation generative-modeling computer-vision machine-learning-research image-synthesis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

34

Forks

2

Language

Jupyter Notebook

License

MIT

Last pushed

Oct 03, 2023

Commits (30d)

0

Get this data via API

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

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