Depth-Anything-V3: Optimized for Qualcomm Devices

Depth Anything 3 (DA3), a model that predicts spatially consistent geometry from arbitrary visual inputs, with or without known camera poses.

This is based on the implementation of Depth-Anything-V3 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 2.50, ONNX Runtime 1.30.0	Download
QNN_DLC	float	Universal	QAIRT 2.50	Download
TFLITE	float	Universal	QAIRT 2.50	Download

For more device-specific assets and performance metrics, visit Depth-Anything-V3 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-V3 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.depth_estimation

Model Stats:

• Input resolution: 518x518
• Model checkpoint: da3-small
• Model size (float): 94.3 MB
• Number of parameters: 24.7M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
Depth-Anything-V3	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	27.978 ms	2 - 444 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	31.634 ms	2 - 436 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® X2 Elite	27.601 ms	5 - 5 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® X Elite	61.926 ms	70 - 70 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® 8 Gen 3 Mobile	43.884 ms	0 - 563 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® 8 Gen 1 Mobile	89.007 ms	6 - 573 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	64.894 ms	3 - 10 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	60.998 ms	0 - 79 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® QCS8450	89.007 ms	6 - 573 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	66.932 ms	3 - 9 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	61.926 ms	70 - 70 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® Dragonwing™ Q-8750	31.634 ms	2 - 436 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	32.004 ms	3 - 455 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	41.364 ms	0 - 427 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® X2 Elite	33.156 ms	3 - 3 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® X Elite	68.86 ms	3 - 3 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	48.897 ms	2 - 575 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	98.896 ms	0 - 568 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	71.683 ms	3 - 10 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	67.691 ms	3 - 6 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA8775P	73.127 ms	2 - 418 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA8650P	73.127 ms	2 - 418 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA8255P	73.127 ms	2 - 418 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® QCS8450	98.896 ms	0 - 568 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	73.42 ms	3 - 9 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	68.86 ms	3 - 3 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	41.364 ms	0 - 427 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA8295P	94.635 ms	0 - 397 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	29.787 ms	0 - 447 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	37.154 ms	1 - 451 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	44.498 ms	1 - 553 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	105.576 ms	1 - 550 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	66.701 ms	1 - 82 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	62.977 ms	0 - 11 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA8775P	68.5 ms	1 - 427 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA8650P	68.5 ms	1 - 427 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA8255P	68.5 ms	1 - 427 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® QCS8450	105.576 ms	1 - 550 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	69.215 ms	1 - 81 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	37.154 ms	1 - 451 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA8295P	102.571 ms	1 - 409 MB	NPU

License

• The license for the original implementation of Depth-Anything-V3 can be found here.

References

• Depth Anything 3: Recovering the visual space from any views
• 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.