karimknaebel/point2vec
[GCPR 2023 | CVPR 2023 Workshop] Self-Supervised Representation Learning on Point Clouds
This tool helps machine learning engineers and researchers to train robust models for understanding 3D data. It takes raw 3D point cloud data as input and produces high-quality feature representations, enabling more accurate classification and segmentation of 3D objects. This is primarily useful for developers working on computer vision tasks involving 3D scenes.
100 stars.
Use this if you need to build or improve computer vision models that analyze and interpret 3D point cloud data for tasks like object recognition or identifying different parts of an object.
Not ideal if you are not a developer or do not have experience with Python, CUDA, and machine learning model training, as it requires setting up a specific development environment.
Stars
100
Forks
10
Language
Python
License
MIT
Category
Last pushed
Jan 26, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/karimknaebel/point2vec"
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