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 2.45, ONNX Runtime 1.25.0	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	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:

• Model checkpoint: da3-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-V3	ONNX	float	Snapdragon® X2 Elite	28.127 ms	5 - 5 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® X Elite	70.474 ms	70 - 70 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® 8 Gen 3 Mobile	55.379 ms	0 - 652 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® 8 Gen 1 Mobile	129.401 ms	2 - 660 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	69.11 ms	4 - 8 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® QCS8450	129.401 ms	2 - 660 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	77.277 ms	3 - 9 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	28.356 ms	2 - 523 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® 8 Elite Mobile	36.647 ms	2 - 499 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® Dragonwing™ Q-8750	36.647 ms	2 - 499 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	70.474 ms	70 - 70 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® X2 Elite	35.283 ms	3 - 3 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® X Elite	79.301 ms	3 - 3 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	61.384 ms	0 - 644 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	152.031 ms	3 - 679 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® QCS8275	186.696 ms	1 - 491 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	79.138 ms	3 - 6 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA8775P	85.478 ms	1 - 491 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA8650P	85.478 ms	1 - 491 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA8255P	85.478 ms	1 - 491 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® QCS8450	152.031 ms	3 - 679 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	85.424 ms	3 - 9 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	33.332 ms	3 - 520 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA7255P	186.696 ms	1 - 491 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Elite Mobile	43.449 ms	2 - 503 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA8295P	118.847 ms	0 - 504 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	43.449 ms	2 - 503 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	79.301 ms	3 - 3 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	54.461 ms	1 - 604 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	120.349 ms	1 - 609 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® QCS8275	180.613 ms	2 - 467 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	74.952 ms	1 - 12 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA8775P	81.181 ms	1 - 467 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA8650P	81.181 ms	1 - 467 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA8255P	81.181 ms	1 - 467 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® QCS8450	120.349 ms	1 - 609 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	81.472 ms	1 - 81 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	30.77 ms	1 - 487 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA7255P	180.613 ms	2 - 467 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Elite Mobile	39.213 ms	0 - 478 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA8295P	103.466 ms	1 - 467 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	39.213 ms	0 - 478 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.