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