knazeri/edge-connect

EdgeConnect: Structure Guided Image Inpainting using Edge Prediction, ICCV 2019 https://arxiv.org/abs/1901.00212

51
/ 100
Established

This tool helps graphic designers, photo editors, and digital artists repair or remove unwanted objects from images. You provide an image with a masked-out region, and it intelligently fills in the missing area, focusing first on reconstructing realistic lines and then adding colors. The output is a complete image that looks as if the original content was never missing.

2,616 stars. No commits in the last 6 months.

Use this if you need to seamlessly repair or remove large, irregular missing sections from photographs or digital art, achieving natural-looking results.

Not ideal if you need a quick, simple fill for small, regular shapes, or if you prefer manual control over every detail of the inpainting process.

photo-editing digital-art image-restoration graphic-design visual-content-creation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

2,616

Forks

533

Language

Python

License

Category

image-inpainting

Last pushed

Feb 03, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/knazeri/edge-connect"

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