NVlabs/ODISE

Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]

41
/ 100
Emerging

This project helps researchers and engineers analyze images by automatically outlining and classifying every object and region, even for categories it hasn't seen before. You provide an image and a text description of what you want to find, and it outputs a detailed, segmented image. It's designed for computer vision scientists and AI practitioners who need to perform advanced image analysis.

934 stars. No commits in the last 6 months.

Use this if you need to precisely segment and identify objects within images using flexible text descriptions, especially for categories not present in standard training datasets.

Not ideal if you're looking for a simple, off-the-shelf image classification tool for a fixed set of categories, or if you don't have expertise in machine learning development.

image-segmentation computer-vision object-detection visual-recognition scene-understanding
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

934

Forks

56

Language

Python

License

Last pushed

Jul 06, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/NVlabs/ODISE"

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