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	1.292 ms	0 - 164 MB	NPU
Midas-V2	ONNX	float	Snapdragon® 8 Elite Mobile	1.479 ms	0 - 163 MB	NPU
Midas-V2	ONNX	float	Snapdragon® X2 Elite	1.314 ms	35 - 35 MB	NPU
Midas-V2	ONNX	float	Snapdragon® X Elite	2.923 ms	35 - 35 MB	NPU
Midas-V2	ONNX	float	Snapdragon® X Elite	2.923 ms	35 - 35 MB	NPU
Midas-V2	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.93 ms	0 - 200 MB	NPU
Midas-V2	ONNX	float	Qualcomm® QCS8550 (Proxy)	2.73 ms	0 - 181 MB	NPU
Midas-V2	ONNX	float	Qualcomm® QCS9075	3.874 ms	1 - 4 MB	NPU
Midas-V2	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.479 ms	0 - 163 MB	NPU
Midas-V2	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.646 ms	0 - 58 MB	NPU
Midas-V2	ONNX	w8a8	Snapdragon® 8 Elite Mobile	0.766 ms	0 - 61 MB	NPU
Midas-V2	ONNX	w8a8	Snapdragon® X2 Elite	0.632 ms	20 - 20 MB	NPU
Midas-V2	ONNX	w8a8	Snapdragon® X Elite	1.488 ms	17 - 17 MB	NPU
Midas-V2	ONNX	w8a8	Snapdragon® X Elite	1.488 ms	17 - 17 MB	NPU
Midas-V2	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	0.938 ms	0 - 95 MB	NPU
Midas-V2	ONNX	w8a8	Qualcomm® QCS8550 (Proxy)	1.355 ms	0 - 24 MB	NPU
Midas-V2	ONNX	w8a8	Qualcomm® QCS9075	1.526 ms	0 - 3 MB	NPU
Midas-V2	ONNX	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.766 ms	0 - 61 MB	NPU
Midas-V2	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.28 ms	1 - 164 MB	NPU
Midas-V2	QNN_DLC	float	Snapdragon® 8 Elite Mobile	1.599 ms	1 - 159 MB	NPU
Midas-V2	QNN_DLC	float	Snapdragon® X2 Elite	1.556 ms	1 - 1 MB	NPU
Midas-V2	QNN_DLC	float	Snapdragon® X Elite	3.295 ms	1 - 1 MB	NPU
Midas-V2	QNN_DLC	float	Snapdragon® X Elite	3.295 ms	1 - 1 MB	NPU
Midas-V2	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.113 ms	0 - 191 MB	NPU
Midas-V2	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	12.075 ms	1 - 158 MB	NPU
Midas-V2	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	3.067 ms	1 - 3 MB	NPU
Midas-V2	QNN_DLC	float	Qualcomm® SA8775P	4.257 ms	1 - 160 MB	NPU
Midas-V2	QNN_DLC	float	Qualcomm® SA8775P	4.257 ms	1 - 160 MB	NPU
Midas-V2	QNN_DLC	float	Qualcomm® SA8775P	4.257 ms	1 - 160 MB	NPU
Midas-V2	QNN_DLC	float	Qualcomm® QCS9075	4.465 ms	1 - 3 MB	NPU
Midas-V2	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	6.833 ms	0 - 192 MB	NPU
Midas-V2	QNN_DLC	float	Qualcomm® SA7255P	12.075 ms	1 - 158 MB	NPU
Midas-V2	QNN_DLC	float	Qualcomm® SA8295P	5.459 ms	1 - 155 MB	NPU
Midas-V2	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.599 ms	1 - 159 MB	NPU
Midas-V2	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.564 ms	0 - 50 MB	NPU
Midas-V2	QNN_DLC	w8a8	Snapdragon® 8 Elite Mobile	0.658 ms	0 - 46 MB	NPU
Midas-V2	QNN_DLC	w8a8	Snapdragon® X2 Elite	0.727 ms	0 - 0 MB	NPU
Midas-V2	QNN_DLC	w8a8	Snapdragon® X Elite	1.464 ms	0 - 0 MB	NPU
Midas-V2	QNN_DLC	w8a8	Snapdragon® X Elite	1.464 ms	0 - 0 MB	NPU
Midas-V2	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	0.917 ms	0 - 81 MB	NPU
Midas-V2	QNN_DLC	w8a8	Qualcomm® QCS6490	4.058 ms	0 - 2 MB	NPU
Midas-V2	QNN_DLC	w8a8	Qualcomm® QCS8275 (Proxy)	2.86 ms	0 - 47 MB	NPU
Midas-V2	QNN_DLC	w8a8	Qualcomm® QCS8550 (Proxy)	1.341 ms	0 - 2 MB	NPU
Midas-V2	QNN_DLC	w8a8	Qualcomm® SA8775P	1.568 ms	0 - 52 MB	NPU
Midas-V2	QNN_DLC	w8a8	Qualcomm® SA8775P	1.568 ms	0 - 52 MB	NPU
Midas-V2	QNN_DLC	w8a8	Qualcomm® SA8775P	1.568 ms	0 - 52 MB	NPU
Midas-V2	QNN_DLC	w8a8	Qualcomm® QCS9075	1.441 ms	0 - 2 MB	NPU
Midas-V2	QNN_DLC	w8a8	Qualcomm® QCM6690	9.056 ms	0 - 173 MB	NPU
Midas-V2	QNN_DLC	w8a8	Qualcomm® QCS8450 (Proxy)	1.854 ms	0 - 81 MB	NPU
Midas-V2	QNN_DLC	w8a8	Qualcomm® SA7255P	2.86 ms	0 - 47 MB	NPU
Midas-V2	QNN_DLC	w8a8	Qualcomm® SA8295P	2.228 ms	0 - 46 MB	NPU
Midas-V2	QNN_DLC	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.658 ms	0 - 46 MB	NPU
Midas-V2	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	1.578 ms	0 - 171 MB	NPU
Midas-V2	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	1.578 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 Elite Mobile	1.606 ms	0 - 178 MB	NPU
Midas-V2	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.108 ms	0 - 227 MB	NPU
Midas-V2	TFLITE	float	Qualcomm® QCS8275 (Proxy)	12.114 ms	0 - 173 MB	NPU
Midas-V2	TFLITE	float	Qualcomm® QCS8550 (Proxy)	3.012 ms	0 - 3 MB	NPU
Midas-V2	TFLITE	float	Qualcomm® SA8775P	4.245 ms	0 - 173 MB	NPU
Midas-V2	TFLITE	float	Qualcomm® SA8775P	4.245 ms	0 - 173 MB	NPU
Midas-V2	TFLITE	float	Qualcomm® SA8775P	4.245 ms	0 - 173 MB	NPU
Midas-V2	TFLITE	float	Qualcomm® QCS9075	4.39 ms	0 - 39 MB	NPU
Midas-V2	TFLITE	float	Qualcomm® QCS8450 (Proxy)	6.831 ms	0 - 215 MB	NPU
Midas-V2	TFLITE	float	Qualcomm® SA7255P	12.114 ms	0 - 173 MB	NPU
Midas-V2	TFLITE	float	Qualcomm® SA8295P	5.496 ms	0 - 155 MB	NPU
Midas-V2	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.606 ms	0 - 178 MB	NPU
Midas-V2	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.488 ms	0 - 48 MB	NPU
Midas-V2	TFLITE	w8a8	Snapdragon® 8 Elite Mobile	0.558 ms	0 - 49 MB	NPU
Midas-V2	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	0.744 ms	0 - 78 MB	NPU
Midas-V2	TFLITE	w8a8	Qualcomm® QCS6490	3.61 ms	0 - 28 MB	NPU
Midas-V2	TFLITE	w8a8	Qualcomm® QCS8275 (Proxy)	2.451 ms	0 - 45 MB	NPU
Midas-V2	TFLITE	w8a8	Qualcomm® QCS8550 (Proxy)	1.088 ms	0 - 4 MB	NPU
Midas-V2	TFLITE	w8a8	Qualcomm® SA8775P	1.346 ms	0 - 48 MB	NPU
Midas-V2	TFLITE	w8a8	Qualcomm® SA8775P	1.346 ms	0 - 48 MB	NPU
Midas-V2	TFLITE	w8a8	Qualcomm® SA8775P	1.346 ms	0 - 48 MB	NPU
Midas-V2	TFLITE	w8a8	Qualcomm® QCS9075	1.174 ms	0 - 20 MB	NPU
Midas-V2	TFLITE	w8a8	Qualcomm® QCM6690	8.382 ms	0 - 170 MB	NPU
Midas-V2	TFLITE	w8a8	Qualcomm® QCS8450 (Proxy)	1.597 ms	0 - 78 MB	NPU
Midas-V2	TFLITE	w8a8	Qualcomm® SA7255P	2.451 ms	0 - 45 MB	NPU
Midas-V2	TFLITE	w8a8	Qualcomm® SA8295P	1.97 ms	0 - 44 MB	NPU
Midas-V2	TFLITE	w8a8	Snapdragon® 8 Elite For Galaxy Mobile	0.558 ms	0 - 49 MB	NPU
Midas-V2	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	1.347 ms	0 - 168 MB	NPU
Midas-V2	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	1.347 ms	0 - 168 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.