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	2.196 ms	5 - 5 MB	NPU
face_detector	ONNX	float	Snapdragon® X Elite	4.158 ms	5 - 5 MB	NPU
face_detector	ONNX	float	Snapdragon® 8 Gen 3 Mobile	2.496 ms	0 - 164 MB	NPU
face_detector	ONNX	float	Snapdragon® 8 Gen 1 Mobile	6.801 ms	7 - 178 MB	NPU
face_detector	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	4.376 ms	4 - 13 MB	NPU
face_detector	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	3.99 ms	0 - 4 MB	NPU
face_detector	ONNX	float	Qualcomm® QCS8450	6.801 ms	7 - 178 MB	NPU
face_detector	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	4.806 ms	5 - 12 MB	NPU
face_detector	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	4.158 ms	5 - 5 MB	NPU
face_detector	ONNX	float	Qualcomm® Dragonwing™ Q-8750	2.259 ms	0 - 155 MB	NPU
face_detector	ONNX	float	Snapdragon® 8 Elite Mobile	2.259 ms	0 - 155 MB	NPU
face_detector	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	2.081 ms	3 - 158 MB	NPU
face_detector	QNN_DLC	float	Snapdragon® X2 Elite	2.832 ms	5 - 5 MB	NPU
face_detector	QNN_DLC	float	Snapdragon® X Elite	5.809 ms	5 - 5 MB	NPU
face_detector	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	3.505 ms	5 - 170 MB	NPU
face_detector	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	8.348 ms	5 - 61 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	5.395 ms	5 - 13 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	11.566 ms	1 - 149 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	5.236 ms	2 - 4 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® SA8775P	6.338 ms	0 - 152 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® SA8650P	6.338 ms	0 - 152 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® SA8255P	6.338 ms	0 - 152 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® QCS8450	8.348 ms	5 - 61 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	6.084 ms	5 - 12 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	5.809 ms	5 - 5 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	2.809 ms	0 - 154 MB	NPU
face_detector	QNN_DLC	float	Qualcomm® SA7255P	11.566 ms	1 - 149 MB	NPU
face_detector	QNN_DLC	float	Snapdragon® 8 Elite Mobile	2.809 ms	0 - 154 MB	NPU
face_detector	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	2.369 ms	4 - 157 MB	NPU
face_detector	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	3.481 ms	0 - 168 MB	NPU
face_detector	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	8.324 ms	1 - 55 MB	NPU
face_detector	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	5.447 ms	1 - 11 MB	NPU
face_detector	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	11.6 ms	1 - 149 MB	NPU
face_detector	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	5.285 ms	1 - 3 MB	NPU
face_detector	TFLITE	float	Qualcomm® SA8775P	6.362 ms	1 - 154 MB	NPU
face_detector	TFLITE	float	Qualcomm® SA8650P	6.362 ms	1 - 154 MB	NPU
face_detector	TFLITE	float	Qualcomm® SA8255P	6.362 ms	1 - 154 MB	NPU
face_detector	TFLITE	float	Qualcomm® QCS8450	8.324 ms	1 - 55 MB	NPU
face_detector	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	6.089 ms	1 - 10 MB	NPU
face_detector	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	2.787 ms	0 - 154 MB	NPU
face_detector	TFLITE	float	Qualcomm® SA7255P	11.6 ms	1 - 149 MB	NPU
face_detector	TFLITE	float	Qualcomm® SA8295P	7.722 ms	1 - 35 MB	NPU
face_detector	TFLITE	float	Snapdragon® 8 Elite Mobile	2.787 ms	0 - 154 MB	NPU
face_detector	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	2.4 ms	0 - 152 MB	NPU
pose_estimator	ONNX	float	Snapdragon® X2 Elite	1.289 ms	1 - 1 MB	NPU
pose_estimator	ONNX	float	Snapdragon® X Elite	2.617 ms	76 - 76 MB	NPU
pose_estimator	ONNX	float	Snapdragon® 8 Gen 3 Mobile	2.077 ms	0 - 37 MB	NPU
pose_estimator	ONNX	float	Snapdragon® 8 Gen 1 Mobile	5.55 ms	0 - 39 MB	NPU
pose_estimator	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	5.131 ms	0 - 4 MB	NPU
pose_estimator	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	2.711 ms	0 - 81 MB	NPU
pose_estimator	ONNX	float	Qualcomm® QCS8450	5.55 ms	0 - 39 MB	NPU
pose_estimator	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	4.494 ms	0 - 4 MB	NPU
pose_estimator	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	2.617 ms	76 - 76 MB	NPU
pose_estimator	ONNX	float	Qualcomm® Dragonwing™ Q-8750	1.637 ms	0 - 25 MB	NPU
pose_estimator	ONNX	float	Snapdragon® 8 Elite Mobile	1.637 ms	0 - 25 MB	NPU
pose_estimator	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	1.335 ms	0 - 25 MB	NPU
pose_estimator	QNN_DLC	float	Snapdragon® X2 Elite	1.472 ms	1 - 1 MB	NPU
pose_estimator	QNN_DLC	float	Snapdragon® X Elite	2.88 ms	1 - 1 MB	NPU
pose_estimator	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	2.235 ms	0 - 38 MB	NPU
pose_estimator	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	6.532 ms	0 - 40 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	5.156 ms	1 - 4 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	17.823 ms	1 - 25 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	2.773 ms	1 - 2 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® SA8775P	4.84 ms	1 - 26 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® SA8650P	4.84 ms	1 - 26 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® SA8255P	4.84 ms	1 - 26 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® QCS8450	6.532 ms	0 - 40 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	4.645 ms	3 - 5 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	2.88 ms	1 - 1 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	1.723 ms	0 - 28 MB	NPU
pose_estimator	QNN_DLC	float	Qualcomm® SA7255P	17.823 ms	1 - 25 MB	NPU
pose_estimator	QNN_DLC	float	Snapdragon® 8 Elite Mobile	1.723 ms	0 - 28 MB	NPU
pose_estimator	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	1.434 ms	1 - 28 MB	NPU
pose_estimator	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	2.253 ms	0 - 43 MB	NPU
pose_estimator	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	6.499 ms	0 - 46 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	5.125 ms	0 - 78 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	17.413 ms	0 - 26 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	2.847 ms	0 - 3 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® SA8775P	4.807 ms	0 - 27 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® SA8650P	4.807 ms	0 - 27 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® SA8255P	4.807 ms	0 - 27 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® QCS8450	6.499 ms	0 - 46 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	4.641 ms	0 - 78 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	1.71 ms	0 - 31 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® SA7255P	17.413 ms	0 - 26 MB	NPU
pose_estimator	TFLITE	float	Qualcomm® SA8295P	5.337 ms	0 - 27 MB	NPU
pose_estimator	TFLITE	float	Snapdragon® 8 Elite Mobile	1.71 ms	0 - 31 MB	NPU
pose_estimator	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1.381 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.