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 1.27.1	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	26.516 ms	2 - 428 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	32.886 ms	3 - 428 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® X2 Elite	26.657 ms	5 - 5 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® X Elite	64.025 ms	70 - 70 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® 8 Gen 3 Mobile	46.98 ms	1 - 570 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® 8 Gen 1 Mobile	86.038 ms	1 - 567 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	67.9 ms	3 - 10 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	63.787 ms	0 - 79 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® QCS8450	86.038 ms	1 - 567 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	69.336 ms	3 - 9 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	64.025 ms	70 - 70 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® Dragonwing™ Q-8750	32.886 ms	3 - 428 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	32.028 ms	3 - 455 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	41.896 ms	0 - 427 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® X2 Elite	33.291 ms	3 - 3 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® X Elite	68.721 ms	3 - 3 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	49.207 ms	3 - 578 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	100.095 ms	3 - 570 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	71.686 ms	3 - 10 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	67.232 ms	3 - 5 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® QCS8450	100.095 ms	3 - 570 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	73.651 ms	3 - 9 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	68.721 ms	3 - 3 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	41.896 ms	0 - 427 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA8295P	94.619 ms	0 - 397 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	29.769 ms	1 - 448 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	37.111 ms	1 - 451 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	45.055 ms	1 - 554 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	104.42 ms	2 - 551 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	66.808 ms	1 - 82 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	62.515 ms	1 - 12 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA8775P	68.485 ms	1 - 427 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA8650P	68.485 ms	1 - 427 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA8255P	68.485 ms	1 - 427 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® QCS8450	104.42 ms	2 - 551 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	69.324 ms	1 - 81 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	37.111 ms	1 - 451 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA8295P	102.562 ms	1 - 410 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.