mit-han-lab/e3d
Efficient 3D Deep Learning
This is a collection of resources for machine learning engineers and researchers focused on making 3D deep learning models run faster and more efficiently. It helps you process raw 3D point cloud data, like that from LiDAR sensors, and convert it into optimized neural network architectures for tasks like object detection or scene understanding. The primary users are deep learning practitioners working on 3D computer vision applications, especially in areas like autonomous vehicles.
No commits in the last 6 months.
Use this if you are a deep learning engineer or researcher who needs to build or optimize 3D perception models that process point cloud data efficiently, especially for real-time applications.
Not ideal if you are a beginner looking for a simple, out-of-the-box solution for basic 3D data visualization or processing without deep learning components.
Stars
47
Forks
—
Language
—
License
—
Category
Last pushed
Mar 19, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mit-han-lab/e3d"
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