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 2.45, ONNX Runtime 1.27.1	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 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® X2 Elite	2.207 ms	5 - 5 MB	NPU
face_detector	ONNX	float	Snapdragon® X Elite	4.213 ms	5 - 5 MB	NPU
face_detector	ONNX	float	Snapdragon® 8 Gen 3 Mobile	2.507 ms	0 - 166 MB	NPU
face_detector	ONNX	float	Snapdragon® 8 Gen 1 Mobile	6.78 ms	7 - 175 MB	NPU
face_detector	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	4.358 ms	4 - 13 MB	NPU
face_detector	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.99 ms	0 - 28 MB	NPU
face_detector	ONNX	float	Qualcomm® QCS8450	6.78 ms	7 - 175 MB	NPU
face_detector	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	4.779 ms	5 - 12 MB	NPU
face_detector	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	4.213 ms	5 - 5 MB	NPU
face_detector	ONNX	float	Qualcomm® Dragonwing™ Q-8750	2.259 ms	3 - 157 MB	NPU
face_detector	ONNX	float	Snapdragon® 8 Elite Mobile	2.259 ms	3 - 157 MB	NPU
face_detector	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	2.083 ms	0 - 155 MB	NPU
face_detector	QNN_DLC	float	Snapdragon® X2 Elite	2.86 ms	5 - 5 MB	NPU
face_detector	QNN_DLC	float	Snapdragon® X Elite	5.762 ms	5 - 5 MB	NPU
face_detector	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	3.488 ms	5 - 170 MB	NPU
face_detector	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	8.296 ms	5 - 60 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	5.388 ms	5 - 13 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	5.228 ms	5 - 95 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® SA8775P	6.345 ms	0 - 152 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	8.296 ms	5 - 60 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	6.076 ms	5 - 12 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	5.762 ms	5 - 5 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	2.81 ms	0 - 148 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® SA7255P	11.602 ms	1 - 149 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® SA8295P	7.737 ms	0 - 34 MB	NPU
face_detector	QNN_DLC	float	Snapdragon® 8 Elite Mobile	2.81 ms	0 - 148 MB	NPU
face_detector	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	2.375 ms	1 - 154 MB	NPU
face_detector	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	3.512 ms	1 - 169 MB	NPU
face_detector	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	8.312 ms	1 - 55 MB	NPU
face_detector	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	5.437 ms	1 - 11 MB	NPU
face_detector	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	5.286 ms	1 - 4 MB	NPU
face_detector	TFLITE	float	Qualcomm® SA8775P	6.339 ms	1 - 154 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	8.312 ms	1 - 55 MB	NPU
face_detector	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	6.097 ms	1 - 10 MB	NPU
face_detector	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	2.79 ms	0 - 153 MB	NPU
face_detector	TFLITE	float	Qualcomm® SA7255P	11.647 ms	1 - 149 MB	NPU
face_detector	TFLITE	float	Qualcomm® SA8295P	7.719 ms	1 - 35 MB	NPU
face_detector	TFLITE	float	Snapdragon® 8 Elite Mobile	2.79 ms	0 - 153 MB	NPU
face_detector	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	2.413 ms	0 - 152 MB	NPU
pose_estimator	ONNX	float	Snapdragon® X2 Elite	1.297 ms	2 - 2 MB	NPU
pose_estimator	ONNX	float	Snapdragon® X Elite	2.607 ms	76 - 76 MB	NPU
pose_estimator	ONNX	float	Snapdragon® 8 Gen 3 Mobile	2.076 ms	0 - 38 MB	NPU
pose_estimator	ONNX	float	Snapdragon® 8 Gen 1 Mobile	5.552 ms	0 - 39 MB	NPU
pose_estimator	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	5.127 ms	0 - 4 MB	NPU
pose_estimator	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	2.722 ms	0 - 81 MB	NPU
pose_estimator	ONNX	float	Qualcomm® QCS8450	5.552 ms	0 - 39 MB	NPU
pose_estimator	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	4.497 ms	0 - 4 MB	NPU
pose_estimator	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	2.607 ms	76 - 76 MB	NPU
pose_estimator	ONNX	float	Qualcomm® Dragonwing™ Q-8750	1.638 ms	0 - 24 MB	NPU
pose_estimator	ONNX	float	Snapdragon® 8 Elite Mobile	1.638 ms	0 - 24 MB	NPU
pose_estimator	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	1.337 ms	0 - 26 MB	NPU
pose_estimator	QNN_DLC	float	Snapdragon® X2 Elite	1.474 ms	1 - 1 MB	NPU
pose_estimator	QNN_DLC	float	Snapdragon® X Elite	2.866 ms	1 - 1 MB	NPU
pose_estimator	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.235 ms	0 - 39 MB	NPU
pose_estimator	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	6.537 ms	0 - 40 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	5.152 ms	1 - 4 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	2.771 ms	1 - 187 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® SA8775P	4.812 ms	1 - 26 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	6.537 ms	0 - 40 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	4.66 ms	3 - 5 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	2.866 ms	1 - 1 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	1.689 ms	1 - 27 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® SA7255P	17.806 ms	1 - 25 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® SA8295P	5.407 ms	1 - 22 MB	NPU
pose_estimator	QNN_DLC	float	Snapdragon® 8 Elite Mobile	1.689 ms	1 - 27 MB	NPU
pose_estimator	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.433 ms	1 - 28 MB	NPU
pose_estimator	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.241 ms	0 - 43 MB	NPU
pose_estimator	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	6.503 ms	0 - 46 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	5.127 ms	0 - 78 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	2.85 ms	0 - 3 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® SA8775P	4.812 ms	0 - 27 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	6.503 ms	0 - 46 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	4.643 ms	0 - 78 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	1.704 ms	0 - 27 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® SA7255P	17.38 ms	0 - 26 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® SA8295P	5.347 ms	0 - 22 MB	NPU
pose_estimator	TFLITE	float	Snapdragon® 8 Elite Mobile	1.704 ms	0 - 27 MB	NPU
pose_estimator	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.38 ms	0 - 28 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.