Talegqz/unsupervised_co_part_segmentation

[ICML2021] Unsupervised Co-part Segmentation through Assembly

29
/ 100
Experimental

This project helps computer vision researchers automatically break down moving objects in videos into their distinct, meaningful parts, without needing to label any data beforehand. You feed it a video of, say, a dancing human, and it outputs a segmented video showing each body part (like an arm or leg) as a separate component. It's designed for researchers working on advanced video analysis and understanding tasks.

No commits in the last 6 months.

Use this if you need to identify and separate the individual moving components of objects within videos, especially when you don't have labeled data for training.

Not ideal if you're looking for a simple, out-of-the-box video editing tool or if your main goal is static image segmentation rather than analyzing motion-based parts in videos.

video-analysis motion-segmentation unsupervised-learning computer-vision-research object-part-identification
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

45

Forks

6

Language

Python

License

Last pushed

Dec 23, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Talegqz/unsupervised_co_part_segmentation"

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