Gorilla-Lab-SCUT/SSTNet

Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks

36
/ 100
Emerging

This project helps you accurately identify and separate individual objects within complex 3D scans of indoor environments. You input a 3D point cloud, which is like a digital scan of a room, and it outputs a detailed segmentation where each object (like a chair, table, or lamp) is uniquely identified and outlined. This is ideal for professionals in robotics, virtual reality, or architectural modeling who work with 3D scene data.

111 stars. No commits in the last 6 months.

Use this if you need to precisely distinguish and isolate individual objects from a raw 3D scan of an indoor scene for tasks like inventory, scene understanding, or digital twin creation.

Not ideal if you are working with 2D images, outdoor scenes, or require only a general understanding of scene categories rather than individual object boundaries.

3D-scanning robotics architecture-modeling virtual-reality augmented-reality
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

111

Forks

9

Language

Python

License

MIT

Last pushed

Nov 16, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Gorilla-Lab-SCUT/SSTNet"

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