LTU-RAI/sga-dpcc
Official page for SGA-DPCC (Scene Graph-Aware Deep Point Cloud Compression), accepted @ RA-L'25, to be presented @ ICRA'26
This project helps roboticists and autonomous vehicle developers efficiently transmit 3D environmental data. It takes raw 3D point cloud scans from LiDAR sensors and compresses them significantly, outputting much smaller, semantically enriched data that can be used for tasks like robot localization or map building. This is designed for teams working with centralized or decentralized multi-robot systems where bandwidth and connectivity are often limited.
Use this if you need to drastically reduce the size of 3D point cloud data from LiDAR sensors while maintaining accuracy for robotic perception tasks in bandwidth-constrained environments.
Not ideal if your primary need is general-purpose image or video compression, or if you are not working with 3D point cloud data in a robotic or autonomous vehicle context.
Stars
22
Forks
—
Language
Python
License
MIT
Category
Last pushed
Jan 05, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/LTU-RAI/sga-dpcc"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
daavoo/pyntcloud
pyntcloud is a Python library for working with 3D point clouds.
yangyanli/PointCNN
PointCNN: Convolution On X-Transformed Points (NeurIPS 2018)
torch-points3d/torch-points3d
Pytorch framework for doing deep learning on point clouds.
yogeshhk/MidcurveNN
Computation of Midcurve of Thin Polygons using Neural Networks
charlesq34/pointnet2
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space