OpenGVLab/DDPS

Official Implementation of "Denoising Diffusion Semantic Segmentation with Mask Prior Modeling"

25
/ 100
Experimental

This project improves the accuracy of semantic segmentation, which is the task of labeling every pixel in an image with a category like 'road', 'building', or 'person'. It takes an image as input and outputs a more precise segmentation mask. Computer vision engineers, researchers, and practitioners working on image analysis applications would find this useful.

No commits in the last 6 months.

Use this if you need to achieve highly accurate and detailed image segmentation for tasks like autonomous driving, medical imaging, or satellite imagery analysis.

Not ideal if you are looking for a simple, out-of-the-box solution without diving into model configurations or if raw speed is your absolute top priority over precision.

image-segmentation computer-vision image-analysis object-recognition machine-vision
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

73

Forks

4

Language

Python

License

Last pushed

Jul 27, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/OpenGVLab/DDPS"

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