JizhiziLi/matting-survey
Deep Image Matting: A Comprehensive Survey
This is a comprehensive overview of techniques for extracting precise foreground objects from images, even when edges are soft or transparent. It takes an input image and, in some cases, additional hints like a coarse outline or text description, to output a detailed 'alpha matte' that cleanly separates the object from its background. Image editors, graphic designers, and content creators who frequently perform background removal or object extraction will find this valuable.
201 stars. No commits in the last 6 months.
Use this if you need to understand the various methods and advancements in accurately cutting out subjects, like people or products, from complex images for editing or compositing.
Not ideal if you are looking for a ready-to-use software tool or a simple step-by-step tutorial on how to perform image matting.
Stars
201
Forks
17
Language
—
License
—
Category
Last pushed
May 16, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JizhiziLi/matting-survey"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MarcoForte/FBA_Matting
Official repository for the paper F, B, Alpha Matting
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...