nsavinov/semantic3dnet
Point cloud semantic segmentation via Deep 3D Convolutional Neural Network
This project helps classify individual points within large 3D scans (point clouds) into meaningful categories like buildings, cars, or vegetation. It takes raw 3D point cloud data as input and outputs a classified point cloud, where each point is labeled with its semantic class. This tool is for researchers and practitioners working with detailed 3D spatial data who need to automatically understand and segment objects within their scans.
188 stars. No commits in the last 6 months.
Use this if you need to automatically categorize millions of points in a 3D scan into semantic classes, such as for urban planning, autonomous vehicle perception, or environmental mapping.
Not ideal if you don't have access to a powerful Nvidia GPU with at least 6GB of memory and 8GB of system RAM, or if you need to classify objects in 2D images instead of 3D point clouds.
Stars
188
Forks
77
Language
C++
License
BSD-3-Clause
Category
Last pushed
Aug 30, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/nsavinov/semantic3dnet"
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,...
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
NazirNayal8/RbA
Official code for RbA: Segmenting Unknown Regions Rejected by All (ICCV 2023)