vivoCameraResearch/SDMatte

Official code for our ICCV2025 paper "SDMatte: Grafting Diffusion Models for Interactive Matting"

35
/ 100
Emerging

This project helps graphic designers, photographers, and marketers precisely cut out objects from images, even those with intricate edges like hair or fur. You provide an image and simple visual cues (like points, boxes, or rough masks), and the system outputs a perfectly matted image with the background removed. It's designed for anyone needing high-quality image cutouts for compositing, product showcases, or creative projects.

178 stars. No commits in the last 6 months.

Use this if you need to extract foreground objects with exceptional detail from complex backgrounds in a user-friendly, interactive way.

Not ideal if you need fully automated background removal without any user interaction or if you're working with video rather than still images.

image-editing graphic-design photo-retouching visual-marketing digital-art
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 8 / 25

How are scores calculated?

Stars

178

Forks

7

Language

Python

License

MIT

Last pushed

Aug 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/vivoCameraResearch/SDMatte"

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