SixDRepNet: Optimized for Qualcomm Devices

6DRepNet predicts head pose (pitch, yaw, roll) from a face image using a RepVGG-B1g2 backbone and a continuous 6D rotation representation, achieving robust and accurate head pose estimation.

This is based on the implementation of SixDRepNet 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 SixDRepNet 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 SixDRepNet on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.pose_estimation

Model Stats:

• Input resolution: 224x224
• Model size (float): 58.4 MB
• Number of parameters: 15.3M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
face_detector	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	1.859 ms	0 - 145 MB	NPU
face_detector	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	2.09 ms	0 - 148 MB	NPU
face_detector	ONNX	float	Snapdragon® X2 Elite	1.904 ms	5 - 5 MB	NPU
face_detector	ONNX	float	Snapdragon® X Elite	3.858 ms	5 - 5 MB	NPU
face_detector	ONNX	float	Snapdragon® 8 Gen 3 Mobile	2.544 ms	0 - 163 MB	NPU
face_detector	ONNX	float	Snapdragon® 8 Gen 1 Mobile	5.679 ms	7 - 172 MB	NPU
face_detector	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	4.409 ms	4 - 13 MB	NPU
face_detector	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.768 ms	3 - 6 MB	NPU
face_detector	ONNX	float	Qualcomm® QCS8450	5.679 ms	7 - 172 MB	NPU
face_detector	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	4.557 ms	5 - 13 MB	NPU
face_detector	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	3.858 ms	5 - 5 MB	NPU
face_detector	ONNX	float	Qualcomm® Dragonwing™ Q-8750	2.09 ms	0 - 148 MB	NPU
face_detector	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	2.061 ms	5 - 151 MB	NPU
face_detector	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	2.784 ms	0 - 143 MB	NPU
face_detector	QNN_DLC	float	Snapdragon® X2 Elite	2.37 ms	5 - 5 MB	NPU
face_detector	QNN_DLC	float	Snapdragon® X Elite	5.483 ms	5 - 5 MB	NPU
face_detector	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	3.443 ms	5 - 165 MB	NPU
face_detector	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	8.209 ms	5 - 62 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	5.37 ms	5 - 13 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	4.976 ms	5 - 6 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® SA8650P	6.345 ms	0 - 152 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® SA8255P	6.345 ms	0 - 152 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® QCS8450	8.209 ms	5 - 62 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	5.974 ms	5 - 13 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	5.483 ms	5 - 5 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	2.784 ms	0 - 143 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® SA8295P	7.497 ms	1 - 36 MB	NPU
face_detector	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	2.053 ms	0 - 145 MB	NPU
face_detector	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	2.773 ms	0 - 143 MB	NPU
face_detector	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	3.522 ms	0 - 159 MB	NPU
face_detector	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	8.245 ms	1 - 58 MB	NPU
face_detector	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	5.388 ms	1 - 11 MB	NPU
face_detector	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	4.979 ms	1 - 7 MB	NPU
face_detector	TFLITE	float	Qualcomm® SA8650P	6.339 ms	1 - 154 MB	NPU
face_detector	TFLITE	float	Qualcomm® SA8255P	6.339 ms	1 - 154 MB	NPU
face_detector	TFLITE	float	Qualcomm® QCS8450	8.245 ms	1 - 58 MB	NPU
face_detector	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	6.013 ms	1 - 10 MB	NPU
face_detector	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	2.773 ms	0 - 143 MB	NPU
face_detector	TFLITE	float	Qualcomm® SA8295P	7.531 ms	1 - 36 MB	NPU
pose_estimator	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	1.319 ms	0 - 29 MB	NPU
pose_estimator	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1.441 ms	0 - 29 MB	NPU
pose_estimator	ONNX	float	Snapdragon® X2 Elite	1.29 ms	2 - 2 MB	NPU
pose_estimator	ONNX	float	Snapdragon® X Elite	2.457 ms	75 - 75 MB	NPU
pose_estimator	ONNX	float	Snapdragon® 8 Gen 3 Mobile	1.786 ms	0 - 43 MB	NPU
pose_estimator	ONNX	float	Snapdragon® 8 Gen 1 Mobile	4.305 ms	0 - 43 MB	NPU
pose_estimator	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	5.023 ms	0 - 5 MB	NPU
pose_estimator	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	2.423 ms	0 - 105 MB	NPU
pose_estimator	ONNX	float	Qualcomm® QCS8450	4.305 ms	0 - 43 MB	NPU
pose_estimator	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	4.444 ms	1 - 4 MB	NPU
pose_estimator	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	2.457 ms	75 - 75 MB	NPU
pose_estimator	ONNX	float	Qualcomm® Dragonwing™ Q-8750	1.441 ms	0 - 29 MB	NPU
pose_estimator	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	1.372 ms	1 - 35 MB	NPU
pose_estimator	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	1.576 ms	1 - 31 MB	NPU
pose_estimator	QNN_DLC	float	Snapdragon® X2 Elite	1.457 ms	1 - 1 MB	NPU
pose_estimator	QNN_DLC	float	Snapdragon® X Elite	2.855 ms	1 - 1 MB	NPU
pose_estimator	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	1.951 ms	0 - 41 MB	NPU
pose_estimator	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	4.939 ms	0 - 45 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	5.125 ms	1 - 4 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	2.676 ms	1 - 2 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® SA8650P	4.812 ms	1 - 26 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® SA8255P	4.812 ms	1 - 26 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® QCS8450	4.939 ms	0 - 45 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	4.635 ms	1 - 3 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	2.855 ms	1 - 1 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	1.576 ms	1 - 31 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® SA8295P	5.21 ms	1 - 26 MB	NPU
pose_estimator	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	1.369 ms	0 - 33 MB	NPU
pose_estimator	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1.557 ms	0 - 32 MB	NPU
pose_estimator	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1.944 ms	0 - 49 MB	NPU
pose_estimator	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	4.926 ms	0 - 51 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	5.143 ms	0 - 79 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	2.636 ms	0 - 2 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® SA8650P	4.812 ms	0 - 27 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® SA8255P	4.812 ms	0 - 27 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® QCS8450	4.926 ms	0 - 51 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	4.629 ms	0 - 78 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	1.557 ms	0 - 32 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® SA8295P	5.223 ms	0 - 26 MB	NPU

License

• The license for the original implementation of SixDRepNet can be found here.

References

• 6D Rotation Representation for Unconstrained Head Pose Estimation
• 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.