VCG-team/DiffSegmenter

Official implementation for "Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter"

23
/ 100
Experimental

This project helps computer vision practitioners analyze images by identifying and outlining specific objects or regions within them, even for categories it hasn't been explicitly trained on. You input images, and it outputs segmentation masks that clearly define different objects. It's designed for researchers or engineers working on image analysis and understanding.

No commits in the last 6 months.

Use this if you need to precisely segment objects in images, including novel or uncommon categories, without the need for extensive training data or model retraining.

Not ideal if you require real-time inference on edge devices or if your primary need is general object detection without fine-grained pixel-level segmentation.

Image Analysis Computer Vision Object Segmentation Scene Understanding Visual AI
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

54

Forks

2

Language

Jupyter Notebook

License

Last pushed

Sep 26, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/VCG-team/DiffSegmenter"

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