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 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.43	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	22.395 ms	5 - 833 MB	NPU
Depth-Anything-V2	ONNX	float	Snapdragon® X2 Elite	23.307 ms	51 - 51 MB	NPU
Depth-Anything-V2	ONNX	float	Snapdragon® X Elite	56.886 ms	50 - 50 MB	NPU
Depth-Anything-V2	ONNX	float	Snapdragon® 8 Gen 3 Mobile	37.764 ms	5 - 876 MB	NPU
Depth-Anything-V2	ONNX	float	Qualcomm® QCS8550 (Proxy)	54.391 ms	0 - 68 MB	NPU
Depth-Anything-V2	ONNX	float	Qualcomm® QCS9075	71.179 ms	3 - 9 MB	NPU
Depth-Anything-V2	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	30.529 ms	2 - 756 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	20.204 ms	3 - 492 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Snapdragon® X2 Elite	22.625 ms	3 - 3 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Snapdragon® X Elite	55.53 ms	3 - 3 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	38.507 ms	2 - 610 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	144.009 ms	1 - 467 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	53.802 ms	3 - 6 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® SA8775P	59.188 ms	1 - 464 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® QCS9075	76.017 ms	3 - 9 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	90.466 ms	2 - 564 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® SA7255P	144.009 ms	1 - 467 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Qualcomm® SA8295P	81.351 ms	0 - 455 MB	NPU
Depth-Anything-V2	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	26.81 ms	0 - 469 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.