mbzuai-metaverse/XMem2

A tool for efficient semi-supervised video object segmentation (great results with minimal manual labor) and a dataset for benchmarking

43
/ 100
Emerging

This tool helps video editors, animators, and VFX artists efficiently isolate specific objects or subjects throughout an entire video clip. You provide a few marked frames indicating the objects, and the tool automatically generates precise masks for all other frames, even for challenging, deforming, or fluid objects like hair. This significantly reduces the manual effort needed for tasks like rotoscoping.

207 stars. No commits in the last 6 months.

Use this if you need to precisely segment objects across many frames of a video with minimal manual input, especially for complex or moving subjects.

Not ideal if you only need to segment a single static image or if your video objects are very simple and require no advanced tracking.

video-editing animation VFX rotoscoping motion-graphics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

207

Forks

31

Language

Python

License

GPL-3.0

Last pushed

Mar 13, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/mbzuai-metaverse/XMem2"

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