PeterL1n/RobustVideoMatting
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
This project helps video editors and content creators easily remove backgrounds from videos, similar to a green screen effect but without needing a green screen. You input any video of a person, and it outputs a video where the person is perfectly cut out from their original background, ready to be placed into a new scene. This is ideal for anyone producing video content who needs professional-looking subject isolation.
9,264 stars. No commits in the last 6 months.
Use this if you need to cleanly separate a person from their video background without special equipment, for tasks like virtual backgrounds, video compositing, or creating transparent video overlays.
Not ideal if your primary need is static image background removal or if you require isolating non-human subjects from video.
Stars
9,264
Forks
1,192
Language
Python
License
GPL-3.0
Category
Last pushed
Apr 02, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/PeterL1n/RobustVideoMatting"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
patrikhuber/eos
A lightweight 3D Morphable Face Model library in modern C++
Uason-Chen/CTR-GCN
[ICCV2021] Official code for "Channel-wise Topology Refinement Graph Convolution for...
PeterL1n/BackgroundMattingV2
Real-Time High-Resolution Background Matting
Zielon/MICA
MICA - Towards Metrical Reconstruction of Human Faces [ECCV2022]
BGU-CS-VIL/DeepMCBM
"A Deep Moving-camera Background Model" [Erez, Shapira Weber, and Freifeld, ECCV 2022]