Hugging Face's logo

qualcomm
/
Midas-V2

Depth Estimation
PyTorch
android
Model card Files
xet
 Community

Midas-V2: Optimized for Qualcomm Devices

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 pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

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.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime Precision Chipset SDK Versions Download
ONNX float Universal QAIRT 2.42, ONNX Runtime 1.24.3 Download
ONNX w8a8 Universal QAIRT 2.42, ONNX Runtime 1.24.3 Download
QNN_DLC float Universal QAIRT 2.45 Download
QNN_DLC w8a8 Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download
TFLITE w8a8 Universal QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit Midas-V2 on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

  • Custom weights (e.g., fine-tuned checkpoints)
  • Custom input shapes
  • Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for Midas-V2 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.depth_estimation

Model Stats:

  • Model checkpoint: MiDaS_small
  • Input resolution: 256x256
  • Number of parameters: 16.6M
  • Model size (float): 63.2 MB
  • Model size (w8a8): 16.9 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
Midas-V2 ONNX float Snapdragon® 8 Elite Gen 5 Mobile 1.29 ms 0 - 162 MB NPU
Midas-V2 ONNX float Snapdragon® X2 Elite 1.315 ms 35 - 35 MB NPU
Midas-V2 ONNX float Snapdragon® X Elite 2.931 ms 35 - 35 MB NPU
Midas-V2 ONNX float Snapdragon® 8 Gen 3 Mobile 1.924 ms 0 - 200 MB NPU
Midas-V2 ONNX float Qualcomm® QCS8550 (Proxy) 2.729 ms 0 - 41 MB NPU
Midas-V2 ONNX float Qualcomm® QCS9075 3.878 ms 1 - 4 MB NPU
Midas-V2 ONNX float Snapdragon® 8 Elite For Galaxy Mobile 1.478 ms 0 - 162 MB NPU
Midas-V2 ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.647 ms 0 - 58 MB NPU
Midas-V2 ONNX w8a8 Snapdragon® X2 Elite 0.628 ms 20 - 20 MB NPU
Midas-V2 ONNX w8a8 Snapdragon® X Elite 1.517 ms 17 - 17 MB NPU
Midas-V2 ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.939 ms 0 - 96 MB NPU
Midas-V2 ONNX w8a8 Qualcomm® QCS8550 (Proxy) 1.332 ms 0 - 25 MB NPU
Midas-V2 ONNX w8a8 Qualcomm® QCS9075 1.536 ms 0 - 3 MB NPU
Midas-V2 ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.764 ms 0 - 61 MB NPU
Midas-V2 QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 1.281 ms 1 - 164 MB NPU
Midas-V2 QNN_DLC float Snapdragon® X2 Elite 1.566 ms 1 - 1 MB NPU
Midas-V2 QNN_DLC float Snapdragon® X Elite 3.273 ms 1 - 1 MB NPU
Midas-V2 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 2.116 ms 1 - 195 MB NPU
Midas-V2 QNN_DLC float Qualcomm® QCS8275 (Proxy) 12.09 ms 1 - 158 MB NPU
Midas-V2 QNN_DLC float Qualcomm® QCS8550 (Proxy) 3.041 ms 1 - 2 MB NPU
Midas-V2 QNN_DLC float Qualcomm® SA8775P 4.223 ms 1 - 159 MB NPU
Midas-V2 QNN_DLC float Qualcomm® QCS9075 4.46 ms 3 - 5 MB NPU
Midas-V2 QNN_DLC float Qualcomm® QCS8450 (Proxy) 6.801 ms 0 - 192 MB NPU
Midas-V2 QNN_DLC float Qualcomm® SA7255P 12.09 ms 1 - 158 MB NPU
Midas-V2 QNN_DLC float Qualcomm® SA8295P 5.451 ms 0 - 154 MB NPU
Midas-V2 QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 1.616 ms 1 - 160 MB NPU
Midas-V2 QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.572 ms 0 - 51 MB NPU
Midas-V2 QNN_DLC w8a8 Snapdragon® X2 Elite 0.726 ms 0 - 0 MB NPU
Midas-V2 QNN_DLC w8a8 Snapdragon® X Elite 1.49 ms 0 - 0 MB NPU
Midas-V2 QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.901 ms 0 - 81 MB NPU
Midas-V2 QNN_DLC w8a8 Qualcomm® QCS6490 4.085 ms 0 - 2 MB NPU
Midas-V2 QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 2.851 ms 0 - 47 MB NPU
Midas-V2 QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 1.329 ms 0 - 8 MB NPU
Midas-V2 QNN_DLC w8a8 Qualcomm® SA8775P 1.565 ms 0 - 50 MB NPU
Midas-V2 QNN_DLC w8a8 Qualcomm® QCS9075 1.439 ms 0 - 2 MB NPU
Midas-V2 QNN_DLC w8a8 Qualcomm® QCM6690 8.97 ms 0 - 173 MB NPU
Midas-V2 QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 1.858 ms 0 - 81 MB NPU
Midas-V2 QNN_DLC w8a8 Qualcomm® SA7255P 2.851 ms 0 - 47 MB NPU
Midas-V2 QNN_DLC w8a8 Qualcomm® SA8295P 2.221 ms 0 - 47 MB NPU
Midas-V2 QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.66 ms 0 - 51 MB NPU
Midas-V2 QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 1.583 ms 0 - 171 MB NPU
Midas-V2 TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 1.279 ms 0 - 175 MB NPU
Midas-V2 TFLITE float Snapdragon® 8 Gen 3 Mobile 2.109 ms 0 - 226 MB NPU
Midas-V2 TFLITE float Qualcomm® QCS8275 (Proxy) 12.139 ms 0 - 173 MB NPU
Midas-V2 TFLITE float Qualcomm® QCS8550 (Proxy) 3.049 ms 0 - 3 MB NPU
Midas-V2 TFLITE float Qualcomm® SA8775P 4.271 ms 0 - 172 MB NPU
Midas-V2 TFLITE float Qualcomm® QCS9075 4.388 ms 0 - 39 MB NPU
Midas-V2 TFLITE float Qualcomm® QCS8450 (Proxy) 6.83 ms 0 - 213 MB NPU
Midas-V2 TFLITE float Qualcomm® SA7255P 12.139 ms 0 - 173 MB NPU
Midas-V2 TFLITE float Qualcomm® SA8295P 5.481 ms 0 - 162 MB NPU
Midas-V2 TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 1.605 ms 0 - 171 MB NPU
Midas-V2 TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.492 ms 0 - 48 MB NPU
Midas-V2 TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.746 ms 0 - 78 MB NPU
Midas-V2 TFLITE w8a8 Qualcomm® QCS6490 3.659 ms 0 - 28 MB NPU
Midas-V2 TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 2.473 ms 0 - 44 MB NPU
Midas-V2 TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 1.074 ms 0 - 1 MB NPU
Midas-V2 TFLITE w8a8 Qualcomm® SA8775P 1.361 ms 0 - 46 MB NPU
Midas-V2 TFLITE w8a8 Qualcomm® QCS9075 1.194 ms 0 - 20 MB NPU
Midas-V2 TFLITE w8a8 Qualcomm® QCM6690 8.357 ms 0 - 171 MB NPU
Midas-V2 TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 1.609 ms 0 - 79 MB NPU
Midas-V2 TFLITE w8a8 Qualcomm® SA7255P 2.473 ms 0 - 44 MB NPU
Midas-V2 TFLITE w8a8 Qualcomm® SA8295P 1.971 ms 0 - 44 MB NPU
Midas-V2 TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.556 ms 0 - 43 MB NPU
Midas-V2 TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 1.345 ms 0 - 168 MB NPU

License

  • The license for the original implementation of Midas-V2 can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Depth Estimation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/Midas-V2