README.md

PyDNet on mobile devices v2.0

This repository contains the source code to run PyDNet on mobile devices.

What's new?

In v2.0, we changed the procedure and the data used for training. More information will be provided soon...

Moreover, we build also a web-based demonstration of the same network! You can try it now here. The model runs directly on your browser, so anything to install!

iOS

The iOS demo has been developed by Giulio Zaccaroni.

XCode is required to build the app, moreover you need to sign in with your AppleID and trust yourself as certified developer.

Android

The code will be released soon

License

Code is licensed under APACHE version 2.0 license. Weights of the network can be used for research purposes only.

Contacts and links

If you use this code in your projects, please cite our paper:

@article{aleotti2020real,
  title={Real-time single image depth perception in the wild with handheld devices},
  author={Aleotti, Filippo and Zaccaroni, Giulio and Bartolomei, Luca and Poggi, Matteo and Tosi, Fabio and Mattoccia, Stefano},
  journal={Sensors},
  volume={21},
  year={2021}
}

@inproceedings{pydnet18,
  title     = {Towards real-time unsupervised monocular depth estimation on CPU},
  author    = {Poggi, Matteo and
               Aleotti, Filippo and
               Tosi, Fabio and
               Mattoccia, Stefano},
  booktitle = {IEEE/JRS Conference on Intelligent Robots and Systems (IROS)},
  year = {2018}
}

More info about the work can be found at these links:

• Real-time single image depth perception in the wild with handheld devices, Arxiv
• PyDNet paper
• PyDNet code

For questions, please send an email to [email protected]