Depth-Anything-V2: Optimized for Qualcomm Devices

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

This is based on the implementation of Depth-Anything-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	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.24.1	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
QNN_DLC	w8a16	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.17.0	Download

For more device-specific assets and performance metrics, visit Depth-Anything-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 Depth-Anything-V2 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.depth_estimation

Model Stats:

• Model checkpoint: DepthAnything_V2_Small
• Input resolution: 518x518
• Number of parameters: 24.7M
• Model size (float): 94.3 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Depth-Anything-V2	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	34.932 ms	5 - 660 MB	NPU
Depth-Anything-V2	ONNX	float	Snapdragon® X2 Elite	34.537 ms	51 - 51 MB	NPU
Depth-Anything-V2	ONNX	float	Snapdragon® X Elite	79.524 ms	50 - 50 MB	NPU
Depth-Anything-V2	ONNX	float	Snapdragon® 8 Gen 3 Mobile	55.754 ms	0 - 860 MB	NPU
Depth-Anything-V2	ONNX	float	Qualcomm® QCS8550 (Proxy)	76.517 ms	0 - 55 MB	NPU
Depth-Anything-V2	ONNX	float	Qualcomm® QCS9075	99.348 ms	3 - 9 MB	NPU
Depth-Anything-V2	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	41.369 ms	2 - 585 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	36.256 ms	3 - 504 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Snapdragon® X2 Elite	34.614 ms	3 - 3 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Snapdragon® X Elite	76.414 ms	3 - 3 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	54.524 ms	0 - 663 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	176.776 ms	1 - 486 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	74.579 ms	3 - 586 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® SA8775P	80.893 ms	1 - 496 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® QCS9075	96.744 ms	3 - 9 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	115.335 ms	1 - 602 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® SA7255P	176.776 ms	1 - 486 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® SA8295P	106.18 ms	0 - 484 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	40.889 ms	3 - 495 MB	NPU
Depth-Anything-V2	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	31.362 ms	1 - 466 MB	NPU
Depth-Anything-V2	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	50.93 ms	1 - 597 MB	NPU
Depth-Anything-V2	TFLITE	float	Qualcomm® QCS8275 (Proxy)	173.774 ms	1 - 445 MB	NPU
Depth-Anything-V2	TFLITE	float	Qualcomm® QCS8550 (Proxy)	72.51 ms	1 - 13 MB	NPU
Depth-Anything-V2	TFLITE	float	Qualcomm® SA8775P	79.064 ms	1 - 445 MB	NPU
Depth-Anything-V2	TFLITE	float	Qualcomm® QCS9075	89.585 ms	1 - 58 MB	NPU
Depth-Anything-V2	TFLITE	float	Qualcomm® QCS8450 (Proxy)	105.734 ms	1 - 583 MB	NPU
Depth-Anything-V2	TFLITE	float	Qualcomm® SA7255P	173.774 ms	1 - 445 MB	NPU
Depth-Anything-V2	TFLITE	float	Qualcomm® SA8295P	100.238 ms	1 - 471 MB	NPU
Depth-Anything-V2	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	35.332 ms	1 - 458 MB	NPU

License

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

References

• Depth Anything V2
• 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.