hkchengrex/MiVOS

[CVPR 2021] Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion. Semi-supervised VOS as well!

45
/ 100
Emerging

This project helps video editors and content creators quickly and accurately isolate moving objects in video footage. You provide a video and use simple on-screen interactions like scribbling to mark the object of interest, and it generates a precise mask that tracks the object across all frames. This tool is ideal for anyone needing to segment specific elements in video for effects, rotoscoping, or analysis.

484 stars. No commits in the last 6 months.

Use this if you need to precisely track and mask one or more objects across an entire video with minimal effort, leveraging interactive input.

Not ideal if you need fully automated segmentation without any user interaction, or if your primary goal is semi-supervised evaluation on large datasets.

video-editing rotoscoping content-creation visual-effects motion-tracking
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

484

Forks

63

Language

Python

License

MIT

Last pushed

Nov 15, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/hkchengrex/MiVOS"

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