Daniil-Selikhanovych/ASBM

PyTorch implementation of "Adversarial Schrödinger Bridge Matching" (NeurIPS 2024)

34
/ 100
Emerging

This project offers a sophisticated method for transforming one collection of images into another, even when there's no direct correspondence between individual images. It takes a dataset of images from a source domain (e.g., photos of males) and a dataset from a target domain (e.g., photos of females), and produces a model that can convert images from the source style to the target style. This is primarily useful for machine learning researchers and practitioners working on advanced image-to-image translation problems.

No commits in the last 6 months.

Use this if you need to perform high-quality, unpaired image-to-image translation between two distinct visual domains.

Not ideal if you are looking for a simple, out-of-the-box solution for basic image editing or style transfer with direct input-output pairs.

image-to-image-translation generative-modeling unsupervised-learning computer-vision deep-learning-research
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

29

Forks

3

Language

Jupyter Notebook

License

Last pushed

Jun 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Daniil-Selikhanovych/ASBM"

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