kuixu/3d-deep-learning
3D Deep Learning works
This project helps researchers and engineers working with 3D data to classify, segment, and detect objects, as well as reconstruct and generate 3D models. It provides a curated collection of deep learning techniques, taking in various 3D data formats like point clouds or volumetric data and outputting identified objects, segmented regions, or new 3D shapes. Anyone involved in computer vision, robotics, or medical imaging who needs to process and interpret complex 3D scenes would use this.
142 stars. No commits in the last 6 months.
Use this if you are a deep learning practitioner exploring state-of-the-art methods for 3D computer vision tasks such as identifying objects in 3D scans or segmenting organs in medical images.
Not ideal if you are looking for a ready-to-use application or a simplified API without needing to understand the underlying research papers and code implementations.
Stars
142
Forks
36
Language
—
License
MIT
Category
Last pushed
May 10, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kuixu/3d-deep-learning"
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