Gorilla-Lab-SCUT/SSTNet
Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks
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.
Stars
111
Forks
9
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
JonasSchult/Mask3D
Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet,...
nsavinov/semantic3dnet
Point cloud semantic segmentation via Deep 3D Convolutional Neural Network
PRBonn/LiDAR-MOS
(LMNet) Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting...
yanx27/2DPASS
2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds (ECCV 2022) :fire:
ctu-vras/traversability_estimation
Semantic Segmentation of Images and Point Clouds for Traversability Estimation