carpedm20/simulated-unsupervised-tensorflow

TensorFlow implementation of "Learning from Simulated and Unsupervised Images through Adversarial Training"

51
/ 100
Established

This project helps machine learning engineers improve the realism of synthetic images for computer vision tasks, particularly eye tracking. You provide simulated images and real-world images, and it outputs refined synthetic images that look more like real ones. This is useful for researchers and developers building systems that rely on large datasets of realistic images, especially when real data is scarce or expensive to collect.

577 stars. No commits in the last 6 months.

Use this if you need to make synthetic datasets generated from tools like UnityEyes appear more natural and indistinguishable from real-world images for training vision models.

Not ideal if you are looking for a pre-trained model for direct application without custom training or if your task doesn't involve refining simulated image data.

computer-vision image-synthesis gaze-tracking dataset-generation machine-learning-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

577

Forks

145

Language

Python

License

Apache-2.0

Last pushed

Dec 10, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/carpedm20/simulated-unsupervised-tensorflow"

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