philferriere/tfvos

Semi-Supervised Video Object Segmentation (VOS) with Tensorflow. Includes implementation of *MaskRNN: Instance Level Video Object Segmentation (NIPS 2017)* as part of the NIPS Paper Implementation Challenge.

45
/ 100
Emerging

This project helps video editors, content creators, or anyone working with video footage to precisely track and isolate specific objects throughout a video. It takes a video and a single labeled image (typically the first frame) indicating the object of interest, then outputs a series of masks and bounding boxes that outline that object in every subsequent frame. This is useful for tasks like special effects, content moderation, or scene analysis.

155 stars. No commits in the last 6 months.

Use this if you need to automatically segment a particular object across an entire video, given only an initial outline of that object.

Not ideal if you need a complete, actively maintained tool, as this implementation is incomplete and no longer under development.

video-editing computer-vision object-tracking content-analysis 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

155

Forks

28

Language

Jupyter Notebook

License

MIT

Last pushed

Dec 06, 2018

Commits (30d)

0

Get this data via API

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

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