Python scripts for performing stereo depth estimation using the HITNET Tensorflow model from Google Research.
Stereo depth estimation on the cones images from the Middlebury dataset (https://vision.middlebury.edu/stereo/data/scenes2003/)
- OpenCV, numpy and tensorflo. pafy (
pip install git+https://github.com/zizo-pro/pafy@b8976f22c19e4ab5515cacbfae0a3970370c102b
) and youtube-dl are required for youtube video inference. - For the drivingStereo dataset, download the data from: https://drivingstereo-dataset.github.io/
Download the tensorflow models from the original repository and save them into the models folder.
- Image inference:
python imageDepthEstimation.py
- Video inference:
python videoDepthEstimation.py
- DrivingStereo dataset inference:
python drivingStereoTest.py
- Hitnet model: https://github.com/google-research/google-research/tree/master/hitnet
- DrivingStereo dataset: https://drivingstereo-dataset.github.io/
- Original paper: https://arxiv.org/abs/2007.12140