cgtuebingen/Flex-Convolution
Source code for: Flex-Convolution (Million-Scale Point-Cloud Learning Beyond Grid-Worlds), accepted at ACCV 2018
This project offers a specialized method for analyzing 3D point cloud data, allowing you to segment and classify objects within large, unstructured spatial datasets. You input raw 3D point clouds, and it outputs segmented categories or labels for each point, helping identify different parts of an object or scene. This tool is designed for researchers and engineers working with large-scale 3D scanning or spatial data analysis.
119 stars. No commits in the last 6 months.
Use this if you need to efficiently process and understand millions of points in a 3D point cloud to perform tasks like object segmentation or scene understanding.
Not ideal if your data is primarily in a regular grid format like traditional 2D images, or if you don't work with 3D point clouds at all.
Stars
119
Forks
11
Language
C++
License
Apache-2.0
Category
Last pushed
Jun 16, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cgtuebingen/Flex-Convolution"
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