Talegqz/unsupervised_co_part_segmentation
[ICML2021] Unsupervised Co-part Segmentation through Assembly
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.
Stars
45
Forks
6
Language
Python
License
—
Category
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.
Higher-rated alternatives
deepinv/deepinv
DeepInverse: a PyTorch library for solving imaging inverse problems using deep learning
yjxiong/tsn-pytorch
Temporal Segment Networks (TSN) in PyTorch
mhamilton723/STEGO
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
fidler-lab/polyrnn-pp
Inference Code for Polygon-RNN++ (CVPR 2018)
pyxu-org/pyxu
Modular and scalable computational imaging in Python with GPU/out-of-core computing.