Hugging Face's logo

qualcomm
/
MediaPipe-Selfie-Segmentation

Image Segmentation
PyTorch
android
Model card Files
xet
 Community

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 2.42, ONNX Runtime 1.24.3 Download
ONNX w8a16 Universal QAIRT 2.42, ONNX Runtime 1.24.3 Download
ONNX w8a8 Universal QAIRT 2.42, ONNX Runtime 1.24.3 Download
QNN_DLC float Universal QAIRT 2.43 Download
QNN_DLC w8a16 Universal QAIRT 2.43 Download
QNN_DLC w8a8 Universal QAIRT 2.43 Download
TFLITE float Universal QAIRT 2.43, TFLite 2.19.1 Download
TFLITE w8a8 Universal QAIRT 2.43, TFLite 2.19.1 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:

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

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 Mobile 0.369 ms 0 - 30 MB NPU
MediaPipe-Selfie-Segmentation ONNX float Snapdragon® X2 Elite 0.382 ms 0 - 0 MB NPU
MediaPipe-Selfie-Segmentation ONNX float Snapdragon® X Elite 0.917 ms 2 - 2 MB NPU
MediaPipe-Selfie-Segmentation ONNX float Snapdragon® 8 Gen 3 Mobile 0.517 ms 0 - 37 MB NPU
MediaPipe-Selfie-Segmentation ONNX float Qualcomm® QCS8550 (Proxy) 0.79 ms 1 - 3 MB NPU
MediaPipe-Selfie-Segmentation ONNX float Qualcomm® QCS9075 0.985 ms 1 - 4 MB NPU
MediaPipe-Selfie-Segmentation ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.411 ms 0 - 24 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.384 ms 0 - 37 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Snapdragon® X2 Elite 0.394 ms 0 - 0 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Snapdragon® X Elite 0.987 ms 1 - 1 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.552 ms 0 - 40 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Qualcomm® QCS6490 27.206 ms 16 - 18 MB CPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Qualcomm® QCS8550 (Proxy) 0.835 ms 0 - 3 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Qualcomm® QCS9075 0.968 ms 0 - 3 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Qualcomm® QCM6690 11.749 ms 15 - 22 MB CPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.447 ms 0 - 30 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 7.941 ms 14 - 22 MB CPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.191 ms 0 - 30 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Snapdragon® X2 Elite 0.183 ms 0 - 0 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Snapdragon® X Elite 0.48 ms 1 - 1 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.258 ms 0 - 37 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Qualcomm® QCS6490 12.614 ms 8 - 11 MB CPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Qualcomm® QCS8550 (Proxy) 0.36 ms 0 - 3 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Qualcomm® QCS9075 0.513 ms 0 - 3 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Qualcomm® QCM6690 5.898 ms 5 - 12 MB CPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.206 ms 0 - 25 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 4.137 ms 0 - 9 MB CPU
MediaPipe-Selfie-Segmentation QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.315 ms 0 - 30 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Snapdragon® X2 Elite 0.45 ms 1 - 1 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Snapdragon® X Elite 0.821 ms 1 - 1 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.457 ms 0 - 36 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® QCS8275 (Proxy) 1.787 ms 1 - 26 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® QCS8550 (Proxy) 0.686 ms 1 - 18 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® SA8775P 0.997 ms 0 - 27 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® QCS9075 0.841 ms 1 - 3 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® QCS8450 (Proxy) 0.94 ms 0 - 39 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® SA7255P 1.787 ms 1 - 26 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® SA8295P 1.289 ms 0 - 25 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 0.358 ms 0 - 26 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.269 ms 0 - 31 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Snapdragon® X2 Elite 0.381 ms 0 - 0 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Snapdragon® X Elite 0.765 ms 0 - 0 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.423 ms 0 - 37 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® QCS6490 1.829 ms 0 - 3 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 1.336 ms 0 - 27 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 0.603 ms 0 - 2 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® SA8775P 0.833 ms 0 - 29 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® QCS9075 0.727 ms 0 - 2 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® QCM6690 2.085 ms 0 - 138 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 0.766 ms 0 - 39 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® SA7255P 1.336 ms 0 - 27 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® SA8295P 1.107 ms 0 - 24 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.331 ms 0 - 31 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 0.612 ms 0 - 26 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.134 ms 0 - 25 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Snapdragon® X2 Elite 0.236 ms 0 - 0 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.18 ms 0 - 32 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® QCS6490 0.867 ms 0 - 2 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 0.683 ms 0 - 24 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 0.266 ms 0 - 2 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® SA8775P 0.45 ms 0 - 25 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® QCS9075 0.39 ms 2 - 4 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® QCM6690 0.85 ms 0 - 23 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 0.339 ms 0 - 34 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® SA7255P 0.683 ms 0 - 24 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® SA8295P 0.641 ms 0 - 21 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.146 ms 0 - 22 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.262 ms 0 - 23 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.318 ms 0 - 30 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Snapdragon® 8 Gen 3 Mobile 0.46 ms 0 - 35 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® QCS8275 (Proxy) 1.805 ms 0 - 25 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® QCS8550 (Proxy) 0.704 ms 0 - 29 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® SA8775P 1.004 ms 0 - 27 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® QCS9075 0.848 ms 0 - 3 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® QCS8450 (Proxy) 0.945 ms 0 - 38 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® SA7255P 1.805 ms 0 - 25 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® SA8295P 1.312 ms 0 - 25 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 0.365 ms 0 - 25 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.141 ms 0 - 25 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.186 ms 0 - 31 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® QCS6490 0.82 ms 0 - 3 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 0.716 ms 0 - 23 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 0.269 ms 0 - 2 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® SA8775P 0.468 ms 0 - 24 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® QCS9075 0.372 ms 0 - 2 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® QCM6690 0.854 ms 0 - 21 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 0.353 ms 0 - 33 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® SA7255P 0.716 ms 0 - 23 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® SA8295P 0.638 ms 0 - 20 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.15 ms 0 - 22 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.262 ms 0 - 21 MB NPU

License

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

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Image Segmentation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support