roeiherz/CanonicalSg2Im

Code for "Learning Canonical Representations for Scene Graph to Image Generation", Herzig & Bar et al., ECCV2020

32
/ 100
Emerging

This project helps researchers and developers create realistic images from structured descriptions of scenes. You input a 'scene graph' – a diagram showing objects and their relationships (e.g., 'a cat sitting on a mat') – and the system generates a corresponding image. It's particularly useful for those working on computer vision tasks like synthetic data generation or visual storytelling.

No commits in the last 6 months.

Use this if you need to generate high-quality, complex images from textual or graphical scene descriptions, especially when dealing with many objects or detailed spatial relationships.

Not ideal if you're looking for a user-friendly, out-of-the-box application for general image editing or generation without prior technical setup.

synthetic-data-generation computer-vision-research image-synthesis visual-content-creation scene-understanding
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

30

Forks

3

Language

Python

License

MIT

Last pushed

Nov 22, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/roeiherz/CanonicalSg2Im"

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