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"
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.
Stars
965
Forks
127
Language
Python
License
MIT
Category
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.
Related tools
yuxumin/PoinTr
[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers
charlesq34/frustum-pointnets
Frustum PointNets for 3D Object Detection from RGB-D Data
drprojects/DeepViewAgg
[CVPR'22 Best Paper Finalist] Official PyTorch implementation of the method presented in...
facebookresearch/votenet
Deep Hough Voting for 3D Object Detection in Point Clouds
Easonyesheng/A2PM-MESA
[CVPR'24 & TPAMI'26] Area to Point Matching Framework