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 2.42, ONNX Runtime 1.24.3	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® 8 Elite Gen 5 Mobile	27.695 ms	5 - 595 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® 8 Elite Mobile	33.926 ms	2 - 594 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® X2 Elite	27.179 ms	71 - 71 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® X Elite	65.531 ms	70 - 70 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® X Elite	65.531 ms	70 - 70 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® 8 Gen 3 Mobile	47.208 ms	5 - 747 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® QCS8550 (Proxy)	64.175 ms	0 - 82 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® QCS9075	83.902 ms	4 - 10 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	33.926 ms	2 - 594 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	33.163 ms	3 - 526 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Elite Mobile	43.239 ms	0 - 499 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® X2 Elite	34.308 ms	3 - 3 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® X Elite	78.518 ms	3 - 3 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® X Elite	78.518 ms	3 - 3 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	59.084 ms	1 - 649 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	185.278 ms	1 - 494 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	78.537 ms	3 - 6 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA8775P	84.759 ms	1 - 494 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA8775P	84.759 ms	1 - 494 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA8775P	84.759 ms	1 - 494 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® QCS9075	99.165 ms	3 - 9 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	150.785 ms	3 - 677 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA7255P	185.278 ms	1 - 494 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA8295P	119.315 ms	3 - 502 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	43.239 ms	0 - 499 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	31.14 ms	1 - 486 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Elite Mobile	38.792 ms	1 - 479 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	55.192 ms	1 - 614 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® QCS8275 (Proxy)	184.468 ms	1 - 473 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® QCS8550 (Proxy)	76.946 ms	1 - 11 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA8775P	83.483 ms	2 - 474 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA8775P	83.483 ms	2 - 474 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA8775P	83.483 ms	2 - 474 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® QCS9075	96.666 ms	1 - 81 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® QCS8450 (Proxy)	122.051 ms	1 - 621 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA7255P	184.468 ms	1 - 473 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA8295P	105.55 ms	0 - 471 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	38.792 ms	1 - 479 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.