NVlabs/GroupViT

Official PyTorch implementation of GroupViT: Semantic Segmentation Emerges from Text Supervision, CVPR 2022.

42
/ 100
Emerging

This project helps computer vision researchers and practitioners automatically identify and group semantically related regions within an image, purely from text descriptions, without needing manually drawn outlines. You provide an image and a text description, and the system outputs an image with distinct regions highlighted and categorized based on the text. It's ideal for those working on advanced image understanding problems.

783 stars. No commits in the last 6 months.

Use this if you need to segment images based on conceptual understanding derived from text, rather than relying on pixel-level mask annotations or pre-defined categories.

Not ideal if you require highly precise, pixel-perfect segmentation masks for every object, or if you don't have access to textual descriptions for your image data.

image-segmentation computer-vision-research zero-shot-learning image-analysis visual-understanding
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

783

Forks

56

Language

Python

License

Last pushed

May 10, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/NVlabs/GroupViT"

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