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 2.37, ONNX Runtime 1.23.0	Download
QNN_DLC	float	Universal	QAIRT 2.42	Download
QNN_DLC	w8a16	Universal	QAIRT 2.42	Download
TFLITE	float	Universal	QAIRT 2.42, 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® X Elite	77.26 ms	62 - 62 MB	NPU
Depth-Anything-V2	ONNX	float	Snapdragon® 8 Gen 3 Mobile	61.931 ms	5 - 881 MB	NPU
Depth-Anything-V2	ONNX	float	Qualcomm® QCS8550 (Proxy)	77.542 ms	0 - 79 MB	NPU
Depth-Anything-V2	ONNX	float	Qualcomm® QCS9075	92.451 ms	3 - 9 MB	NPU
Depth-Anything-V2	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	49.42 ms	2 - 853 MB	NPU
Depth-Anything-V2	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	41.745 ms	0 - 796 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Snapdragon® X Elite	75.62 ms	3 - 3 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	54.729 ms	1 - 662 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	175.602 ms	1 - 486 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	74.678 ms	3 - 6 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® SA8775P	80.969 ms	1 - 495 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® QCS9075	96.537 ms	3 - 9 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	115.052 ms	2 - 602 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® SA7255P	175.602 ms	1 - 486 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® SA8295P	106.479 ms	0 - 487 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	40.746 ms	3 - 494 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	36.508 ms	3 - 504 MB	NPU
Depth-Anything-V2	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	51.504 ms	0 - 595 MB	NPU
Depth-Anything-V2	TFLITE	float	Qualcomm® QCS8275 (Proxy)	177.063 ms	1 - 451 MB	NPU
Depth-Anything-V2	TFLITE	float	Qualcomm® QCS8550 (Proxy)	73.159 ms	1 - 9 MB	NPU
Depth-Anything-V2	TFLITE	float	Qualcomm® SA8775P	79.465 ms	1 - 451 MB	NPU
Depth-Anything-V2	TFLITE	float	Qualcomm® QCS9075	89.404 ms	1 - 58 MB	NPU
Depth-Anything-V2	TFLITE	float	Qualcomm® SA7255P	177.063 ms	1 - 451 MB	NPU
Depth-Anything-V2	TFLITE	float	Qualcomm® SA8295P	102.503 ms	1 - 465 MB	NPU
Depth-Anything-V2	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	37.578 ms	1 - 446 MB	NPU
Depth-Anything-V2	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	31.453 ms	1 - 460 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.