Skip to content
/ PRIN Public

Pointwise Rotation-Invariant Network (AAAI 2020)

Notifications You must be signed in to change notification settings

qq456cvb/PRIN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

24 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PRIN

Pointwise Rotation-Invariant Network in PyTorch

News

An improved version of PRIN (SPRIN) is released here and described in PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features, which achieves much better results.

Overview

This repository is the Pytorch implementation of PRIN (Pointwise Rotation-Invariant Network).

Dependencies

Dataset and pretrained weights

Usage

  • For training, run "python train.py --log_dir log --model_path ./model.py --num_workers 4"
  • For testing, run "python test.py --weight_path ./state.pkl --model_path ./model.py --num_workers 4"

License

MIT

References

Our paper is available on https://arxiv.org/abs/1811.09361.

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}
}

About

Pointwise Rotation-Invariant Network (AAAI 2020)

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published