---
license: mit
pipeline_tag: other
tags:
- point-cloud
- rotation-invariance
- part-segmentation
- 3d
---

# PRIN/SPRIN Pretrained Weights

Pretrained checkpoints for [PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features](https://doi.org/10.1109/TPAMI.2021.3130590) (TPAMI 2022), trained on the ShapeNet part segmentation benchmark.

Code: https://github.com/qq456cvb/SPRIN

## Contents

| File | Model | Size |
|---|---|---|
| `epoch250.pt` | SPRIN (sparse PRIN, operates directly on sparse point clouds) | 112 MB |
| `state79.pkl` | PRIN (Point-wise Rotation Invariant Network with spherical voxel convolution) | 1 MB |

## Usage

Download the checkpoints into the corresponding folders of the repository:

```bash
hf download qq456cvb/SPRIN epoch250.pt --local-dir sprin
hf download qq456cvb/SPRIN state79.pkl --local-dir prin
```

Then run the test scripts:

```bash
python sprin/test.py  # loads sprin/epoch250.pt
python prin/test.py   # loads prin/state79.pkl
```

## Citation

```bibtex
@article{you2022prin,
  title={PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features},
  author={You, Yang and Lou, Yujing and Shi, Ruoxi and Liu, Qi and Tai, Yu-Wing and Ma, Lizhuang and Wang, Weiming and Lu, Cewu},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume={44},
  number={12},
  pages={9489--9502},
  year={2022},
  doi={10.1109/TPAMI.2021.3130590}
}
```