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 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.19.1	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	35.095 ms	5 - 604 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® X2 Elite	35.37 ms	71 - 71 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® X Elite	75.211 ms	70 - 70 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® 8 Gen 3 Mobile	58.779 ms	1 - 773 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® QCS8550 (Proxy)	73.946 ms	0 - 88 MB	NPU
Depth-Anything-V3	ONNX	float	Qualcomm® QCS9075	104.259 ms	4 - 10 MB	NPU
Depth-Anything-V3	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	39.306 ms	2 - 602 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	35.048 ms	3 - 638 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® X2 Elite	36.987 ms	3 - 3 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® X Elite	79.103 ms	3 - 3 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	55.367 ms	2 - 778 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	179.461 ms	1 - 567 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	76.641 ms	3 - 5 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA8775P	83.659 ms	1 - 576 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® QCS9075	108.671 ms	3 - 9 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	129.818 ms	3 - 814 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA7255P	179.461 ms	1 - 567 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Qualcomm® SA8295P	119.884 ms	0 - 594 MB	NPU
Depth-Anything-V3	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	41.033 ms	0 - 602 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	30.777 ms	1 - 550 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	48.516 ms	1 - 694 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® QCS8275 (Proxy)	164.563 ms	1 - 530 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® QCS8550 (Proxy)	67.342 ms	1 - 5 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA8775P	73.594 ms	1 - 531 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® QCS9075	86.358 ms	1 - 82 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® QCS8450 (Proxy)	103.493 ms	1 - 697 MB	NPU
Depth-Anything-V3	TFLITE	float	Qualcomm® SA7255P	164.563 ms	1 - 530 MB	NPU
Depth-Anything-V3	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	34.666 ms	1 - 550 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.