Midas is designed for estimating depth at each point in an image.

This is based on the implementation of Midas-V2 found here. This repository contains scripts for optimized on-device export suitable to run on Qualcomm® devices. More details on model performance accross various devices, can be found here.

Sign up to start using Qualcomm AI Hub and run these models on a hosted Qualcomm® device.

Install the package via pip:

pip install "qai-hub-models[midas]"

Once installed, run the following simple CLI demo:

python -m qai_hub_models.models.midas.demo { --quantize w8a8 }

More details on the CLI tool can be found with the --help option. See demo.py for sample usage of the model including pre/post processing scripts. Please refer to our general instructions on using models for more usage instructions.

This repository contains export scripts that produce a model optimized for on-device deployment. This can be run as follows:

python -m qai_hub_models.models.midas.export { --quantize w8a8 }

Additional options are documented with the --help option.

• The license for the original implementation of Midas-V2 can be found here.
• The license for the compiled assets for on-device deployment can be found here

• Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer
• Source Model Implementation

• Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
• For questions or feedback please reach out to us.