MarcoForte/FBA_Matting
Official repository for the paper F, B, Alpha Matting
This project helps graphic designers and photo editors precisely separate a subject from its background in an image. You provide an image along with a 'trimap' – a rough mask indicating definite foreground, definite background, and an 'unknown' region – and it outputs a refined, high-quality cutout of the foreground object, its background, and an alpha matte. This is ideal for anyone needing to flawlessly extract elements for compositing or further editing.
493 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to accurately extract a subject from a complex background in a photo, especially when dealing with fine details like hair or translucent objects.
Not ideal if you need a fully automated solution without any manual input (like a trimap), or if you are working with extremely high-resolution images and have limited GPU memory.
Stars
493
Forks
97
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jun 22, 2023
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MarcoForte/FBA_Matting"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
pypose/pypose
A library for differentiable robotics on manifolds.
snap-research/articulated-animation
Code for Motion Representations for Articulated Animation paper
foamliu/Deep-Image-Matting
Deep Image Matting
dyelax/Adversarial_Video_Generation
A TensorFlow Implementation of "Deep Multi-Scale Video Prediction Beyond Mean Square Error" by...
DeepMotionEditing/deep-motion-editing
An end-to-end library for editing and rendering motion of 3D characters with deep learning...