JIA-Lab-research/SCGAN

The implementation of 'Image synthesis via semantic composition', ICCV2021.

27
/ 100
Experimental

This tool helps researchers and content creators generate realistic images from semantic layouts. You provide a segmented image (like a map showing different objects or regions) and it outputs a corresponding photorealistic image, such as a street scene or a human face. It's used by those who need to visualize concepts or create diverse image datasets from structural information.

No commits in the last 6 months.

Use this if you need to synthesize new, photorealistic images directly from abstract semantic segmentation maps, like generating varied faces from a face mask or cityscapes from a scene layout.

Not ideal if you're looking to edit existing photos, perform simple image filtering, or generate images without semantic guidance.

generative-art computer-graphics image-synthesis visual-content-creation AI-research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

83

Forks

7

Language

Python

License

Last pushed

Mar 03, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/JIA-Lab-research/SCGAN"

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