cuge1995/PointCutMix
our code for paper 'PointCutMix: Regularization Strategy for Point Cloud Classification', Neurocomputing, 2022
This project helps machine learning engineers improve the accuracy and robustness of their 3D point cloud classification models. It takes existing point cloud datasets and mixes them to create new, augmented training data. The output is a more reliable classification model that performs better even when faced with noisy or attacked data.
No commits in the last 6 months.
Use this if you are training deep learning models on 3D point cloud data and need to enhance their performance, especially in terms of accuracy and resistance to data corruption or adversarial attacks.
Not ideal if your task involves other types of data, such as images, text, or time-series, or if you are not working with point cloud classification problems.
Stars
61
Forks
15
Language
Python
License
MIT
Category
Last pushed
Jul 19, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cuge1995/PointCutMix"
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