dgriffiths3/pointnet2-tensorflow2
Pointnet++ modules implemented as tensorflow 2 keras layers.
This project provides specialized building blocks for creating neural networks that process 3D point cloud data. It takes raw 3D point cloud scans as input and helps create models that can classify or segment these shapes, outputting labels or partitioned segments. This is ideal for researchers or engineers working on tasks like 3D object recognition or scene understanding.
No commits in the last 6 months.
Use this if you are a machine learning engineer working with 3D point cloud data and need to build a custom deep learning model in TensorFlow 2 to classify or segment 3D objects.
Not ideal if you need a complete, out-of-the-box PointNet++ solution or prefer working with a different deep learning framework.
Stars
97
Forks
38
Language
C++
License
—
Category
Last pushed
Apr 22, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dgriffiths3/pointnet2-tensorflow2"
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