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 1.24.1	Download
ONNX	w8a8	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a8	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.17.0	Download
TFLITE	w8a8	Universal	QAIRT 2.43, TFLite 2.17.0	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® X2 Elite	1.313 ms	35 - 35 MB	NPU
Midas-V2	ONNX	float	Snapdragon® X Elite	2.929 ms	35 - 35 MB	NPU
Midas-V2	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.923 ms	0 - 200 MB	NPU
Midas-V2	ONNX	float	Qualcomm® QCS8550 (Proxy)	2.737 ms	1 - 4 MB	NPU
Midas-V2	ONNX	float	Qualcomm® QCS9075	3.882 ms	1 - 4 MB	NPU
Midas-V2	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.483 ms	0 - 164 MB	NPU
Midas-V2	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	1.293 ms	1 - 165 MB	NPU
Midas-V2	ONNX	w8a8	Snapdragon® X2 Elite	0.631 ms	20 - 20 MB	NPU
Midas-V2	ONNX	w8a8	Snapdragon® X Elite	1.49 ms	18 - 18 MB	NPU
Midas-V2	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.93 ms	0 - 95 MB	NPU
Midas-V2	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	1.334 ms	0 - 23 MB	NPU
Midas-V2	ONNX	w8a8	Qualcomm® QCS9075	1.522 ms	0 - 3 MB	NPU
Midas-V2	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.777 ms	0 - 59 MB	NPU
Midas-V2	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.648 ms	0 - 58 MB	NPU
Midas-V2	QNN_DLC	float	Snapdragon® X2 Elite	1.583 ms	1 - 1 MB	NPU
Midas-V2	QNN_DLC	float	Snapdragon® X Elite	3.311 ms	1 - 1 MB	NPU
Midas-V2	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.139 ms	0 - 196 MB	NPU
Midas-V2	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	12.13 ms	1 - 159 MB	NPU
Midas-V2	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	3.054 ms	1 - 2 MB	NPU
Midas-V2	QNN_DLC	float	Qualcomm® SA8775P	4.242 ms	0 - 160 MB	NPU
Midas-V2	QNN_DLC	float	Qualcomm® QCS9075	4.492 ms	1 - 3 MB	NPU
Midas-V2	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	6.81 ms	0 - 193 MB	NPU
Midas-V2	QNN_DLC	float	Qualcomm® SA7255P	12.13 ms	1 - 159 MB	NPU
Midas-V2	QNN_DLC	float	Qualcomm® SA8295P	5.487 ms	1 - 156 MB	NPU
Midas-V2	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.613 ms	0 - 161 MB	NPU
Midas-V2	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.271 ms	1 - 165 MB	NPU
Midas-V2	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.71 ms	0 - 0 MB	NPU
Midas-V2	QNN_DLC	w8a8	Snapdragon® X Elite	1.475 ms	0 - 0 MB	NPU
Midas-V2	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.922 ms	0 - 85 MB	NPU
Midas-V2	QNN_DLC	w8a8	Qualcomm® QCS6490	4.189 ms	0 - 2 MB	NPU
Midas-V2	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	2.883 ms	0 - 46 MB	NPU
Midas-V2	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	1.309 ms	0 - 2 MB	NPU
Midas-V2	QNN_DLC	w8a8	Qualcomm® SA8775P	1.603 ms	0 - 50 MB	NPU
Midas-V2	QNN_DLC	w8a8	Qualcomm® QCS9075	1.46 ms	2 - 4 MB	NPU
Midas-V2	QNN_DLC	w8a8	Qualcomm® QCM6690	8.983 ms	0 - 172 MB	NPU
Midas-V2	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	1.908 ms	0 - 80 MB	NPU
Midas-V2	QNN_DLC	w8a8	Qualcomm® SA7255P	2.883 ms	0 - 46 MB	NPU
Midas-V2	QNN_DLC	w8a8	Qualcomm® SA8295P	2.245 ms	0 - 45 MB	NPU
Midas-V2	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.677 ms	0 - 46 MB	NPU
Midas-V2	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	1.596 ms	0 - 169 MB	NPU
Midas-V2	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.565 ms	0 - 51 MB	NPU
Midas-V2	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.121 ms	0 - 232 MB	NPU
Midas-V2	TFLITE	float	Qualcomm® QCS8275 (Proxy)	12.173 ms	0 - 179 MB	NPU
Midas-V2	TFLITE	float	Qualcomm® QCS8550 (Proxy)	3.036 ms	0 - 3 MB	NPU
Midas-V2	TFLITE	float	Qualcomm® SA8775P	4.3 ms	0 - 180 MB	NPU
Midas-V2	TFLITE	float	Qualcomm® QCS9075	4.441 ms	0 - 39 MB	NPU
Midas-V2	TFLITE	float	Qualcomm® QCS8450 (Proxy)	6.873 ms	0 - 217 MB	NPU
Midas-V2	TFLITE	float	Qualcomm® SA7255P	12.173 ms	0 - 179 MB	NPU
Midas-V2	TFLITE	float	Qualcomm® SA8295P	5.503 ms	0 - 160 MB	NPU
Midas-V2	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.618 ms	0 - 177 MB	NPU
Midas-V2	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.273 ms	0 - 179 MB	NPU
Midas-V2	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.76 ms	0 - 79 MB	NPU
Midas-V2	TFLITE	w8a8	Qualcomm® QCS6490	3.687 ms	0 - 28 MB	NPU
Midas-V2	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	2.439 ms	0 - 46 MB	NPU
Midas-V2	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	1.078 ms	0 - 3 MB	NPU
Midas-V2	TFLITE	w8a8	Qualcomm® SA8775P	1.371 ms	0 - 47 MB	NPU
Midas-V2	TFLITE	w8a8	Qualcomm® QCS9075	1.19 ms	0 - 20 MB	NPU
Midas-V2	TFLITE	w8a8	Qualcomm® QCM6690	8.343 ms	0 - 171 MB	NPU
Midas-V2	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	1.569 ms	0 - 78 MB	NPU
Midas-V2	TFLITE	w8a8	Qualcomm® SA7255P	2.439 ms	0 - 46 MB	NPU
Midas-V2	TFLITE	w8a8	Qualcomm® SA8295P	1.992 ms	0 - 43 MB	NPU
Midas-V2	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.591 ms	0 - 49 MB	NPU
Midas-V2	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	1.356 ms	0 - 170 MB	NPU
Midas-V2	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.483 ms	0 - 49 MB	NPU

License

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

References

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