Official implementation of "Rethinking Rotation Invariance with Point Cloud Registration", AAAI 2023
To build the CUDA kernel for FPS:
pip install pointnet2_ops_lib/.
NOTE: If you encounter problems while building the kernel, you can refer to Pointnet2_PyTorch for solutions.
This repo contains Pytorch implementation of the following modules:
- ModelNet40 Classification under rotations
bash scripts/modelnet_cls.sh - ScanObjectNN Classification under rotations
bash scripts/scanobject_cls.sh - ShapeNetPart Segmentation under rotations
- State-of-the-art accuracy on ModelNet40 under rotation: 91.0% (z/z), 91.0% (z/SO(3)).
- State-of-the-art accuracy on ScanObjectNN OBJ_BG classification under rotation: 86.6% (z/z), 86.3% (z/SO(3)).
- State-of-the-art micro and macro mAP on ShapeNetCore55 under rotation: 0.715, 0.510.
- ShapeNetPart segmentation under rotation: 80.3% (z/z), 80.4% (z/SO(3)).
If you find this repo useful in your work or research, please cite:
Our code borrows a lot from: