thuyngch/Human-Segmentation-PyTorch

Human segmentation models, training/inference code, and trained weights, implemented in PyTorch

42
/ 100
Emerging

This project helps you accurately separate human figures from backgrounds in images or video streams. You provide an image or video, and it outputs a mask highlighting only the human subjects, effectively 'cutting them out' from the scene. It's ideal for developers building applications that require isolating people in visual media, such as for video editing, augmented reality, or privacy-enhancing tools.

574 stars. No commits in the last 6 months.

Use this if you need to programmatically detect and segment human figures from any visual input (images, videos, or live webcam feeds).

Not ideal if you need a no-code solution or if your primary goal is to segment objects other than humans.

image-processing video-analysis computer-vision augmented-reality visual-effects
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 24 / 25

How are scores calculated?

Stars

574

Forks

112

Language

Jupyter Notebook

License

Last pushed

Nov 22, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/thuyngch/Human-Segmentation-PyTorch"

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