pytorch_fpsample
🎉 PyTorch efficient farthest point sampling (FPS) library.
MIT License
Stars
9
Committers
2
PyTorch fpsample
PyTorch efficient farthest point sampling (FPS) implementation, adopted from fpsample.
Currently, this project is under heavy development and not ready for production use. The expected release date is before the end of 2024.
Any contribution is welcome.
Installation
# Install from github
pip install git+https://github.com/leonardodalinky/pytorch_fpsample
# Build locally
pip install .
Usage
import torch_fpsample
x = torch.rand(64, 2048, 3)
sampled_points, indices = torch_fpsample.sample(x, 1024)
> sampled_points.size(), indices.size()
Size([64, 1024, 3]), Size([64, 1024])
Reference
Bucket-based farthest point sampling (QuickFPS) is proposed in the following paper. The implementation is based on the author's Repo (CPU & GPU).
@article{han2023quickfps,
title={QuickFPS: Architecture and Algorithm Co-Design for Farthest Point Sampling in Large-Scale Point Clouds},
author={Han, Meng and Wang, Liang and Xiao, Limin and Zhang, Hao and Zhang, Chenhao and Xu, Xiangrong and Zhu, Jianfeng},
journal={IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems},
year={2023},
publisher={IEEE}
}
Thanks to the authors for their great works.