https://github.com/leonardodalinky/pytorch_fpsample

🎉 PyTorch efficient farthest point sampling (FPS) library.
https://github.com/leonardodalinky/pytorch_fpsample

farthest-point-sampling point-cloud python pytorch

Last synced: 3 months ago
JSON representation

🎉 PyTorch efficient farthest point sampling (FPS) library.

• Host: GitHub
• URL: https://github.com/leonardodalinky/pytorch_fpsample
• Owner: leonardodalinky
• License: mit
• Created: 2024-08-27T08:29:59.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2024-09-03T12:16:21.000Z (4 months ago)
• Last Synced: 2024-09-27T20:03:30.962Z (3 months ago)
• Topics: farthest-point-sampling, point-cloud, python, pytorch
• Language: C++
• Homepage:
• Size: 24.4 KB
• Stars: 9
• Watchers: 1
• Forks: 0
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# PyTorch fpsample

PyTorch efficient farthest point sampling (FPS) implementation, adopted from [fpsample](https://github.com/leonardodalinky/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

```bash

# Install from github

pip install git+https://github.com/leonardodalinky/pytorch_fpsample

# Build locally

pip install .

```

## Usage

```python

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](https://github.com/hanm2019/bucket-based_farthest-point-sampling_CPU) & [GPU](https://github.com/hanm2019/bucket-based_farthest-point-sampling_GPU)).

```bibtex

@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.