ashwmurt/depth_pro

DepthPro: Sharp monocular metric depth in less than a second, on-device

Apple DepthPro is a zero-shot monocular metric depth estimator that emits high-resolution, sharp depth maps from a single 1536x1536 RGB image. The architecture is a multi-scale Vision Transformer built on Dinov2 encoders with DPT-style fusion; alongside the depth map the model predicts a per-image horizontal field of view, which downstream calibration converts into a focal length in pixels. This recipe wraps Apple's HuggingFace checkpoint (apple/DepthPro-hf, ~952M parameters) at the model's native 1536x1536 input resolution.

This is based on the implementation of DepthPro found here. This is a standalone recipe compatible with the Qualcomm® AI Hub Models CLI — it can be compiled and evaluated on real Snapdragon devices via Qualcomm® AI Hub Workbench.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Setup

1. Install the package

Install the base package, fetch this recipe from Hugging Face, then use the qai-hub-models CLI to install the recipe's dependencies:

# NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported.
pip install qai-hub-models
qai-hub-models register ashwmurt/depth_pro
qai-hub-models install depth_pro

register downloads the recipe and names it depth_pro, which is how every command below refers to it.

2. Configure Qualcomm® AI Hub Workbench

Sign-in to Qualcomm® AI Hub Workbench with your Qualcomm® ID. Once signed in navigate to Account -> Settings -> API Token.

With this API token, you can configure your client to run models on the cloud hosted devices.

qai-hub configure --api_token API_TOKEN

Navigate to docs for more information.

Run CLI Demo

Run the following simple CLI demo to verify the model is working end to end:

qai-hub-models demo depth_pro

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.

By default, the demo will run locally in PyTorch. Pass --eval-mode on-device to run the model on a cloud-hosted target device.

Export for on-device deployment

To run the model on Qualcomm® devices, you must export the model for use with an edge runtime such as TensorFlow Lite, ONNX Runtime, or Qualcomm AI Engine Direct. Use the following command to export the model:

qai-hub-models export depth_pro

Additional options are documented with the --help option.

License

• The license for the original implementation of DepthPro can be found here.

References

• Depth Pro: Sharp Monocular Metric Depth in Less Than a Second
• Source Model Implementation

Community

• 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.