PeterL1n/BackgroundMattingV2
Real-Time High-Resolution Background Matting
This tool helps video editors, content creators, and live streamers accurately separate foreground subjects from their backgrounds in high-resolution video, without a green screen. It takes a live video feed or pre-recorded footage, along with a separate image of the plain background, and outputs a clean, 'cut-out' version of the subject, ready for compositing onto a new background. This is for professionals who need high-quality keying for dynamic content.
7,150 stars. No commits in the last 6 months.
Use this if you need to extract people or objects from complex backgrounds in high-resolution video (up to 4K) in real-time, even without a green screen, for professional video production or live broadcasting.
Not ideal if you need a solution that doesn't require a pre-captured background image, or if you don't have access to a powerful NVIDIA GPU for real-time performance.
Stars
7,150
Forks
966
Language
Python
License
MIT
Category
Last pushed
Jun 19, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/PeterL1n/BackgroundMattingV2"
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/RobustVideoMatting
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
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]