griegler/octnet
OctNet: Learning Deep 3D Representations at High Resolutions
This helps computer vision researchers and practitioners efficiently process and analyze complex 3D data like point clouds or mesh models. By converting raw 3D inputs into a specialized octree structure, it reduces the memory and computational demands of deep learning models. This enables the creation of highly detailed 3D object classifications, orientation estimations, and point cloud labeling systems.
505 stars. No commits in the last 6 months.
Use this if you need to train deep neural networks on high-resolution 3D data but are limited by memory or computational resources.
Not ideal if your primary goal is to work with 2D image data or if you require a simpler, out-of-the-box solution for common 3D tasks without delving into custom network architectures.
Stars
505
Forks
104
Language
C++
License
—
Category
Last pushed
Sep 02, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/griegler/octnet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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