drprojects/superpoint_transformer

Official PyTorch implementation of Superpoint Transformer introduced in [ICCV'23] "Efficient 3D Semantic Segmentation with Superpoint Transformer" and SuperCluster introduced in [3DV'24 Oral] "Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering"

58
/ 100
Established

This project helps professionals working with large 3D scene data automatically identify and categorize different objects or regions. It takes raw 3D point cloud data and outputs segmented scenes, where each point is labeled with its corresponding object or semantic class, enabling efficient analysis of complex environments. It is ideal for researchers or engineers analyzing extensive 3D scans.

965 stars.

Use this if you need to perform efficient and accurate semantic or panoptic segmentation on very large 3D point clouds, such as those from LiDAR scans of buildings, outdoor environments, or industrial sites.

Not ideal if your primary task involves processing 2D images, small-scale 3D models, or if you require fine-grained object detection rather than broad segmentation.

3D-scanning point-cloud-analysis environmental-mapping robotics-perception urban-planning
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

965

Forks

127

Language

Python

License

MIT

Last pushed

Feb 24, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/drprojects/superpoint_transformer"

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