linsun449/cliper.code

This repo is the official pytorch implementation of the paper: CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation

17
/ 100
Experimental

This tool helps researchers and computer vision engineers automatically identify and outline various objects within images, even if those objects weren't specifically trained beforehand. You provide an image, and it outputs a detailed segmentation mask that precisely delineates different elements like cars, people, or even specific textures within the scene. It's designed for those working with large image datasets who need flexible, precise object recognition.

No commits in the last 6 months.

Use this if you need to precisely segment a wide variety of objects and regions within images without having to retrain your models for every new category.

Not ideal if you primarily work with a fixed, small set of object categories and require extremely fast processing for real-time applications where every millisecond counts.

image-analysis computer-vision-research visual-content-understanding object-recognition semantic-segmentation
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

40

Forks

Language

Python

License

Last pushed

Sep 10, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/linsun449/cliper.code"

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