hkchengrex/STCN

[NeurIPS 2021] Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation

45
/ 100
Emerging

This tool helps automate the process of precisely outlining moving objects within video footage. You provide a video and a mask or outline of the object in its first frame, and the tool generates a sequence of masks for that object across all subsequent frames. It's designed for video editors, animators, or anyone needing to isolate and track specific elements in video.

562 stars. No commits in the last 6 months.

Use this if you need to quickly and accurately segment a specific object from a video, given its initial position, to create rotoscoping effects or generate precise masks for further processing.

Not ideal if you need to segment multiple objects that frequently appear and disappear, or if you don't have a clear initial segmentation for the object you want to track.

video-editing animation rotoscoping masking visual-effects
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

562

Forks

73

Language

Python

License

MIT

Last pushed

Mar 15, 2024

Commits (30d)

0

Get this data via API

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

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