JonasSchult/Mask3D
Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet, ScanNet200, S3DIS and STPLS3D.
This project helps professionals working with 3D scans of indoor or outdoor environments automatically identify and outline individual objects within those scans. You input raw 3D scan data, and it outputs precise, labeled segments for each distinct object, like chairs, walls, or trees. Architects, urban planners, or surveyors can use this to quickly analyze complex spatial data.
716 stars. No commits in the last 6 months.
Use this if you need to accurately segment specific instances of objects from raw 3D point cloud data of buildings, rooms, or urban landscapes.
Not ideal if your primary goal is general object detection without needing fine-grained individual instance segmentation, or if you're working with 2D images instead of 3D scans.
Stars
716
Forks
126
Language
Python
License
MIT
Category
Last pushed
Oct 29, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/JonasSchult/Mask3D"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
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
NazirNayal8/RbA
Official code for RbA: Segmenting Unknown Regions Rejected by All (ICCV 2023)