https://github.com/Crane-YU/rethink_rotation

[AAAI 2023] Rethinking Rotation Invariance with Point Cloud Registration (official pytorch implementation) https://rotation3d.github.io/
https://github.com/Crane-YU/rethink_rotation

point-cloud rotation-invariant

Last synced: 8 days ago
JSON representation

[AAAI 2023] Rethinking Rotation Invariance with Point Cloud Registration (official pytorch implementation) https://rotation3d.github.io/

• Host: GitHub
• URL: https://github.com/Crane-YU/rethink_rotation
• Owner: Crane-YU
• Created: 2022-12-27T10:20:58.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2022-12-30T07:52:12.000Z (almost 2 years ago)
• Last Synced: 2024-08-01T03:41:27.482Z (3 months ago)
• Topics: point-cloud, rotation-invariant
• Language: Python
• Homepage:
• Size: 2.18 MB
• Stars: 25
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Rethink Rotation

Official implementation of "Rethinking Rotation Invariance with Point Cloud Registration", AAAI 2023

[[Paper]]() [[Supp.]]() [[Video]]()

![img](docs/teaser.png)

## Requirements

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](https://github.com/erikwijmans/Pointnet2_PyTorch) for solutions.

## Code

This repo contains Pytorch implementation of the following modules:

- [x] ModelNet40 Classification under rotations

    ``` 

    bash scripts/modelnet_cls.sh

    ```

- [x] ScanObjectNN Classification under rotations

    ``` 

    bash scripts/scanobject_cls.sh

    ```

- [ ] ShapeNetPart Segmentation under rotations

## Performance

* 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)).

## Citation  

If you find this repo useful in your work or research, please cite:  

## Acknowledgement

Our code borrows a lot from:

- [DGCNN](https://github.com/WangYueFt/dgcnn)

- [DGCNN.pytorch](https://github.com/AnTao97/dgcnn.pytorch)

- [PointContrast](https://github.com/facebookresearch/PointContrast)