CrowdMAC: Masked Crowd Density Completion for Robust Crowd Density Forecasting (WACV'25)

[Paper]

This is the official code release for our WACV 2024 paper
"CrowdMAC: Masked Crowd Density Completion for Robust Crowd Density Forecasting".

🔨 Installation

pip install -r requirements.txt

🔥 Training

1. Pretraining

python train.py

2. Fine-tuning

Place the sdd-pretrained.pth under pretrained folder.

bash finetune.sh

👏 Acknowledgement

We sincerely thank the authors of VideoMAE for providing their source code, which has been invaluable to our work. We are immensely grateful for their contribution.

✍️ Citation

If you use this code for your research, please cite our paper.

@inproceedings{FUJII2025CrowdMAC,
    author = {Ryo Fujii, Ryo Hachiuma, and Hideo Saito},
    title = {CrowdMAC: Masked Crowd Density Completion for Robust Crowd Density Forecasting},
    booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
    year = {2025},
}