MarcoForte/DeepInteractiveSegmentation

Getting to 99% Accuracy in Interactive Segmentation and Interactive Training and Architecture for Deep Object Selection

43
/ 100
Emerging

When editing images, this project helps you quickly and precisely select specific objects or regions, even complex ones, with minimal effort. You provide an image and a few clicks to indicate your target object, and it outputs a highly accurate selection mask. This is ideal for graphic designers, photo editors, and visual artists who need to isolate elements for compositing or further manipulation.

117 stars. No commits in the last 6 months.

Use this if you need to extract objects from images with very high accuracy using minimal manual input.

Not ideal if you need a fully automatic segmentation solution without any interactive input.

image-editing graphic-design photo-manipulation visual-art object-selection
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

117

Forks

18

Language

Jupyter Notebook

License

MIT

Last pushed

Nov 10, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MarcoForte/DeepInteractiveSegmentation"

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