MediaPipe-Selfie-Segmentation: Optimized for Qualcomm Devices

Light-weight model that segments a person from the background in square or landscape selfie and video conference imagery.

This is based on the implementation of MediaPipe-Selfie-Segmentation 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
ONNX	w8a16	Universal	QAIRT 2.50, ONNX Runtime 1.27.1	Download
ONNX	w8a8	Universal	QAIRT 2.50, ONNX Runtime 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.50	Download
QNN_DLC	w8a16	Universal	QAIRT 2.50	Download
QNN_DLC	w8a8	Universal	QAIRT 2.50	Download
TFLITE	float	Universal	QAIRT 2.50	Download
TFLITE	w8a8	Universal	QAIRT 2.50	Download

For more device-specific assets and performance metrics, visit MediaPipe-Selfie-Segmentation 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 MediaPipe-Selfie-Segmentation on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

• Input resolution (Landscape): 144x256
• Input resolution (Square): 256x256
• Model checkpoint: Square
• Model size (float): 447 KB
• Number of output classes: 6
• Number of parameters: 106K

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
MediaPipe-Selfie-Segmentation	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.342 ms	0 - 31 MB	NPU
MediaPipe-Selfie-Segmentation	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.372 ms	0 - 30 MB	NPU
MediaPipe-Selfie-Segmentation	ONNX	float	Snapdragon® X2 Elite	0.365 ms	2 - 2 MB	NPU
MediaPipe-Selfie-Segmentation	ONNX	float	Snapdragon® X Elite	0.701 ms	2 - 2 MB	NPU
MediaPipe-Selfie-Segmentation	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.459 ms	0 - 42 MB	NPU
MediaPipe-Selfie-Segmentation	ONNX	float	Snapdragon® 8 Gen 1 Mobile	0.983 ms	1 - 49 MB	NPU
MediaPipe-Selfie-Segmentation	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	0.878 ms	1 - 5 MB	NPU
MediaPipe-Selfie-Segmentation	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.699 ms	0 - 3 MB	NPU
MediaPipe-Selfie-Segmentation	ONNX	float	Qualcomm® QCS8450	0.983 ms	1 - 49 MB	NPU
MediaPipe-Selfie-Segmentation	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	0.906 ms	1 - 5 MB	NPU
MediaPipe-Selfie-Segmentation	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	0.701 ms	2 - 2 MB	NPU
MediaPipe-Selfie-Segmentation	ONNX	float	Qualcomm® Dragonwing™ Q-8750	0.372 ms	0 - 30 MB	NPU
MediaPipe-Selfie-Segmentation

License

• The license for the original implementation of MediaPipe-Selfie-Segmentation can be found here.

References

• Image segmentation guide
• 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.