nv-tlabs/STEAL
STEAL - Learning Semantic Boundaries from Noisy Annotations (CVPR 2019)
This tool helps computer vision researchers and developers accurately identify object boundaries in images. It takes images with rough or 'noisy' annotations (where the outlines of objects aren't perfectly drawn) and refines them to produce precise semantic boundary maps. This is particularly useful for tasks requiring high-precision object segmentation and analysis.
479 stars. No commits in the last 6 months.
Use this if you need to extract precise object outlines from images, even when your initial image annotations are imperfect or quickly sketched.
Not ideal if you don't work with image data or if you require an off-the-shelf solution without any coding or model setup.
Stars
479
Forks
64
Language
Jupyter Notebook
License
—
Category
Last pushed
Oct 23, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nv-tlabs/STEAL"
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.