yangyanli/PointCNN
PointCNN is a deep learning framework for feature learning from 3D point clouds using X-transformed convolution, published at NeurIPS 2018.
Not currently ranked — collecting fresh signals.
star history
PointCNN provides a convolutional neural network architecture designed specifically for processing unordered 3D point cloud data. It applies an X-transformation to learned weights before convolution to account for the permutation invariance of point sets. The framework achieves state-of-the-art results on point cloud benchmarks including ModelNet40 classification, ShapeNet Parts segmentation, and ScanNet semantic segmentation.
Frequently asked
- What is yangyanli/PointCNN?
- PointCNN is a deep learning framework for feature learning from 3D point clouds using X-transformed convolution, published at NeurIPS 2018.
- Is PointCNN open source?
- Yes — yangyanli/PointCNN is an open-source project tracked on heatdrop.
- What language is PointCNN written in?
- yangyanli/PointCNN is primarily written in Python.
- How popular is PointCNN?
- yangyanli/PointCNN has 1.4k stars on GitHub.
- Where can I find PointCNN?
- yangyanli/PointCNN is on GitHub at https://github.com/yangyanli/PointCNN.