RhythmFormer: Extracting Patterned rPPG Signals based on Periodic Sparse Attention

STEP 1: bash setup.sh

STEP 2: conda activate rppg-toolbox

STEP 3: pip install -r ./requirements.txt

Please use config files under ./configs/infer_configs

For example, if you want to run The model trained on UBFC-rPPG and tested on MMPD, use python main.py --config_file ./configs/infer_configs/UBFC-rPPG_MMPD_RHYTHMFORMER.yaml

Please use config files under ./configs/train_configs

STEP 1: Download the MMPD raw data by asking the paper authors

STEP 2: Modify ./configs/train_configs/intra/0MMPD_RHYTHMFORMER.yaml

STEP 3: Run python main.py --config_file ./configs/train_configs/intra/0MMPD_RHYTHMFORMER.yaml

STEP 1: Download the PURE raw data by asking the paper authors.

STEP 2: Download the UBFC-rPPG raw data via link

STEP 3: Modify ./configs/train_configs/cross/PURE_UBFC-rPPG_RHYTHMFORMER.yaml

STEP 4: Run python main.py --config_file ./configs/train_configs/cross/PURE_UBFC-rPPG_RHYTHMFORMER.yaml

We would like to express sincere thanks to the authors of rPPG-Toolbox, Liu et al., 2023, building upon which, we developed this repo. For detailed usage related instructions, please refer the GitHub repo of the rPPG-Toolbox.

@article{liu2024rppg,
  title={rppg-toolbox: Deep remote ppg toolbox},
  author={Liu, Xin and Narayanswamy, Girish and Paruchuri, Akshay and Zhang, Xiaoyu and Tang, Jiankai and Zhang, Yuzhe and Sengupta, Roni and Patel, Shwetak and Wang, Yuntao and McDuff, Daniel},
  journal={Advances in Neural Information Processing Systems},
  volume={36},
  year={2024}
}

If you find this repository helpful, please consider citing:

@article{zou2025rhythmformer,
    title = {RhythmFormer: Extracting patterned rPPG signals based on periodic sparse attention},
    journal = {Pattern Recognition},
    volume = {164},
    pages = {111511},
    year = {2025},
    issn = {0031-3203},
    doi = {https://doi.org/10.1016/j.patcog.2025.111511},
    url = {https://www.sciencedirect.com/science/article/pii/S0031320325001712},
    author = {Bochao Zou and Zizheng Guo and Jiansheng Chen and Junbao Zhuo and Weiran Huang and Huimin Ma},
    keywords = {Remote physiological measurement, Periodic sparse attention},
}