skgyu/CMOS-GAN

Code for paper "TIP2023 - CMOS-GAN: Semi-supervised Generative Adversarial Model for Cross-Modality Face Image Synthesis"

28
/ 100
Experimental

This tool helps researchers and developers in computer vision and biometrics generate synthetic face images across different modalities. You can input various image types like facial sketches, near-infrared (NIR) photos, or standard RGB photos, and it will output synthesized images in a different modality, such as realistic photos from sketches, visible light images from NIR, or depth maps from RGB. It's designed for those working on improving facial recognition systems or cross-modal image synthesis.

No commits in the last 6 months.

Use this if you need to synthesize diverse face images from one modality to another (e.g., sketch to photo, NIR to visible light, RGB to depth) for research in computer vision or biometrics.

Not ideal if you are looking for an out-of-the-box application for general image editing or require a simple, code-free solution for photo manipulation.

facial recognition image synthesis biometrics computer vision research cross-modal imaging
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

10

Forks

1

Language

Python

License

Apache-2.0

Category

gan-based-t2i

Last pushed

Oct 17, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/skgyu/CMOS-GAN"

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