# Monodepth Demo

[![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/eaidova/openvino_notebooks_binder.git/main?urlpath=git-pull%3Frepo%3Dhttps%253A%252F%252Fgithub.com%252Fopenvinotoolkit%252Fopenvino_notebooks%26urlpath%3Dtree%252Fopenvino_notebooks%252Fnotebooks%2Fvision-monodepth%2Fvision-monodepth.ipynb)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/latest/notebooks/vision-monodepth/vision-monodepth.ipynb)


![monodepth](https://user-images.githubusercontent.com/36741649/127173017-a0bbcf75-db24-4d2c-81b9-616e04ab7cd9.gif)

Monocular Depth Estimation is the task of estimating scene depth using a single image. It has many potential applications in robotics, 3D reconstruction, medical imaging and autonomous systems. This demo uses a neural network model called MiDaS which was developed by the Intelligent Systems Lab at Intel. See their [research paper](https://arxiv.org/abs/1907.01341) to learn more.

## Notebook Contents

This notebook demonstrates Monocular Depth Estimation with the [MidasNet model](https://github.com/openvinotoolkit/open_model_zoo/blob/master/models/public/midasnet/README.md) in OpenVINO.

## Installation Instructions

This is a self-contained example that relies solely on its own code.</br>
We recommend  running the notebook in a virtual environment. You only need a Jupyter server to start.
For details, please refer to [Installation Guide](../../README.md).