Home

Awesome

Point-Query Quadtree for Crowd Counting, Localization, and More (ICCV 2023)

This repository includes the official implementation of the paper:

Point-Query Quadtree for Crowd Counting, Localization, and More

International Conference on Computer Vision (ICCV), 2023

Chengxin Liu<sup>1</sup>, Hao Lu<sup>1</sup>, Zhiguo Cao<sup>1</sup>, Tongliang Liu<sup>2</sup>

<sup>1</sup>Huazhong University of Science and Technology, China

<sup>2</sup>The University of Sydney, Australia

[Paper] | [Supplementary]

PET

Highlights

We formulate crowd counting as a decomposable point querying process, where sparse input points could split into four new points when necessary. This formulation exhibits many appealing properties:

Installation

torch
torchvision
numpy
opencv-python
scipy
matplotlib
pip install -r requirements.txt

Data Preparation

PET
├── data
│    ├── ShanghaiTech
├── datasets
├── models
├── ...

Training

Evaluation

sh eval.sh

Pretrained Models

python==3.8
pytorch==1.12.1
torchvision==0.13.1
DatasetModel LinkTraining LogMAE
ShanghaiTech PartASHA_model.pthSHA_log.txt49.08
ShanghaiTech PartBSHB_model.pthSHB_log.txt6.18
UCF_QNRFUCF_QNRF.pth--
JHU_CrowdJHU_Crowd.pth--
NWPU_CrowdNWPU_Crowd.pth--

Citation

If you find this work helpful for your research, please consider citing:

@InProceedings{liu2023pet,
  title={Point-Query Quadtree for Crowd Counting, Localization, and More},
  author={Liu, Chengxin and Lu, Hao and Cao, Zhiguo and Liu, Tongliang},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2023}
}

Permission

This code is for academic purposes only. Contact: Chengxin Liu (cx_liu@hust.edu.cn)

Acknowledgement

We thank the authors of DETR and P2PNet for open-sourcing their work.