TFLite-MobileStereoNet

Python scripts for performing stereo depth estimation using the MobileStereoNet model in Tensorflow Lite.

MobileStereoNet depth estimation TFLite
Stereo depth estimation on the cones images from the Middlebury dataset (https://vision.middlebury.edu/stereo/data/scenes2003/)

Requirements

  • Check the requirements.txt file. Additionally, pafy and youtube-dl are required for youtube video inference.
  • DrivingStereo dataset, ONLY for the driving_sereo_test.pyscript. Link: https://drivingstereo-dataset.github.io/

Installation

pip install -r requirements.txt
pip install pafy youtube-dl

TFLite model

The original models was converted to different formats (including .tflite) by PINTO0309, the models can be found in his repository.

Original Pytorch model

The Pytorch pretrained model was taken from the original repository.

Examples

  • Image inference:

python image_depth_estimation.py 
  • Video inference:

python video_depth_estimation.py
  • DrivingStereo dataset inference:

python driving_sereo_test.py

Inference video Example

MobileStereoNet depth estimation ONNX

References:

GitHub

View Github