README.md

metadata

license: mit
tags:
  - point-cloud
  - rotation-invariance
  - part-segmentation
  - pytorch
library_name: pytorch

PRIN: Pointwise Rotation-Invariant Network (AAAI 2020) — Pretrained Weights

Pretrained PyTorch weights (state.pkl) for PRIN, from:

Pointwise Rotation-Invariant Network with Adaptive Sampling and 3D Spherical Voxel Convolution (AAAI 2020)

Code and usage instructions: https://github.com/qq456cvb/PRIN

The model is trained on the ShapeNet 17-category part segmentation dataset (unrotated shapes).

Usage

hf download qq456cvb/PRIN state.pkl --local-dir .
python test.py --weight_path ./state.pkl --model_path ./model.py --num_workers 4

Citation

@inproceedings{you2020pointwise,
  title={Pointwise Rotation-Invariant Network with Adaptive Sampling and 3D Spherical Voxel Convolution},
  author={You, Yang and Lou, Yujing and Liu, Qi and Tai, Yu-Wing and Ma, Lizhuang and Lu, Cewu and Wang, Weiming},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={34},
  number={07},
  pages={12717--12724},
  year={2020}
}