I2-Multimedia-Lab/Pointsoup
[IJCAI 2024] Pointsoup: High-Performance and Extremely Low-Decoding-Latency Learned Geometry Codec for Large-Scale Point Cloud Scenes
This project helps professionals working with large 3D point cloud data to drastically reduce the size of their files for storage and transmission, without losing critical detail. It takes uncompressed 3D point cloud scans as input and outputs a much smaller, compressed version that can be quickly decoded for viewing or processing. Architects, urban planners, game developers, and researchers dealing with 3D scanning data would use this.
No commits in the last 6 months.
Use this if you need to compress large 3D point cloud scenes, especially those with sparse surfaces, and require extremely fast decoding speeds for real-time applications or quick access.
Not ideal if your primary concern is absolute highest fidelity at very high bitrates, or if you are working with outdoor LiDAR frames where points are unevenly distributed.
Stars
21
Forks
2
Language
Python
License
MIT
Category
Last pushed
Sep 23, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/I2-Multimedia-Lab/Pointsoup"
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