PointCNN and pointnet2

PointNet++ and PointCNN are competitors—both are hierarchical deep learning architectures for point cloud feature extraction that independently propose different approaches (multi-scale grouping with PointNet blocks vs. X-transformation convolution) to achieve similar goals of learning from unordered 3D point sets.

PointCNN
67
Established
pointnet2
51
Established
Maintenance 16/25
Adoption 10/25
Maturity 16/25
Community 25/25
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 25/25
Stars: 1,428
Forks: 364
Downloads:
Commits (30d): 1
Language: Python
License:
Stars: 3,617
Forks: 931
Downloads:
Commits (30d): 0
Language: Python
License:
No Package No Dependents
Stale 6m No Package No Dependents

About PointCNN

yangyanli/PointCNN

PointCNN: Convolution On X-Transformed Points (NeurIPS 2018)

About pointnet2

charlesq34/pointnet2

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

Implements hierarchical set abstraction layers with multi-scale grouping to capture local geometric structures at increasing receptive fields, addressing non-uniform point cloud densities through adaptive aggregation. Built on TensorFlow with custom CUDA operators for efficient set operations, supporting classification, part segmentation, and semantic scene parsing tasks on ModelNet40, ShapeNet, and ScanNet datasets.

Scores updated daily from GitHub, PyPI, and npm data. How scores work