hahnec/stofnet

StofNet: Super-resolution Time of Flight Network (ICASSP 2024)

StofNet - Super-resolution time of flight Network

Installation

$ python3 -m venv venv

$ source venv/bin/activate

$ python3 -m pip install -r requirements.txt

$ unzip datasets/stof_chirp101_dataset.zip -d datasets/

Training

$ python3 main.py evaluate=False logging=train model=stofnet data_dir=./datasets/stof_chirp101_dataset th=Null rf_scale_factor=10

Inference

$ python3 main.py evaluate=True batch_size=1 etol=1 model=stofnet model_file=different-armadillo data_dir=./datasets/stof_chirp101_dataset logging=Null rf_scale_factor=10 th=Null

Note: More information on commands and settings are found in config.yaml or bash_scripts.

Results

If you use this project for your work, please cite the original paper:

@inproceedings{stofnet,
 title={StofNet: Super-resolution Time of Flight Network}, 
 author={Christopher Hahne and Michel Hayoz and Raphael Sznitman},
 booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
 year={2024},
}

stofnet's Issues

How does it compare with other reasoning pictures？such as EDSR RealESRGAN？