JonasSchult/Mask3D

Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet, ScanNet200, S3DIS and STPLS3D.

50
/ 100
Established

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.

3D-scanning architecture urban-planning surveying spatial-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

716

Forks

126

Language

Python

License

MIT

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.