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 1.24.1 Download
ONNX w8a16 Universal QAIRT 2.42, ONNX Runtime 1.24.1 Download
ONNX w8a8 Universal QAIRT 2.42, ONNX Runtime 1.24.1 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 2.17.0 Download
TFLITE w8a8 Universal QAIRT 2.43, TFLite 2.17.0 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® X Elite 0.941 ms 2 - 2 MB NPU
MediaPipe-Selfie-Segmentation ONNX float Snapdragon® 8 Gen 3 Mobile 0.521 ms 0 - 37 MB NPU
MediaPipe-Selfie-Segmentation ONNX float Qualcomm® QCS8550 (Proxy) 0.783 ms 0 - 34 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 0.412 ms 0 - 30 MB NPU
MediaPipe-Selfie-Segmentation ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.37 ms 0 - 31 MB NPU
MediaPipe-Selfie-Segmentation ONNX float Snapdragon® X2 Elite 0.38 ms 0 - 0 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Snapdragon® X Elite 0.984 ms 1 - 1 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.554 ms 0 - 40 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Qualcomm® QCS6490 30.665 ms 16 - 19 MB CPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Qualcomm® QCS8550 (Proxy) 0.836 ms 0 - 3 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Qualcomm® QCS9075 0.967 ms 0 - 3 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Qualcomm® QCM6690 11.804 ms 14 - 21 MB CPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.446 ms 0 - 36 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 8.339 ms 15 - 23 MB CPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.385 ms 0 - 37 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Snapdragon® X2 Elite 0.391 ms 0 - 0 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Snapdragon® X Elite 0.494 ms 1 - 1 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.252 ms 0 - 36 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Qualcomm® QCS6490 9.583 ms 7 - 11 MB CPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Qualcomm® QCS8550 (Proxy) 0.363 ms 0 - 2 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Qualcomm® QCS9075 0.519 ms 0 - 3 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Qualcomm® QCM6690 5.932 ms 5 - 13 MB CPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.205 ms 0 - 30 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 4.155 ms 0 - 8 MB CPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.19 ms 0 - 30 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Snapdragon® X2 Elite 0.19 ms 0 - 0 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Snapdragon® X Elite 0.854 ms 1 - 1 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.458 ms 0 - 37 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® QCS8275 (Proxy) 1.785 ms 1 - 26 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® QCS8550 (Proxy) 0.681 ms 1 - 2 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® SA8775P 0.996 ms 0 - 28 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® QCS9075 0.842 ms 1 - 3 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® QCS8450 (Proxy) 0.938 ms 0 - 39 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® SA7255P 1.785 ms 1 - 26 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® SA8295P 1.269 ms 1 - 25 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 0.359 ms 0 - 25 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.315 ms 1 - 30 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Snapdragon® X2 Elite 0.435 ms 1 - 1 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Snapdragon® X Elite 0.738 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 1.796 ms 2 - 4 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 1.332 ms 0 - 27 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 0.607 ms 0 - 2 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® SA8775P 3.294 ms 0 - 28 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® QCS9075 0.724 ms 2 - 4 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® QCM6690 2.082 ms 0 - 138 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 0.757 ms 0 - 40 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® SA7255P 1.332 ms 0 - 27 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® SA8295P 1.104 ms 0 - 25 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.33 ms 0 - 31 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 0.616 ms 0 - 26 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.265 ms 0 - 32 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Snapdragon® X2 Elite 0.392 ms 0 - 0 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Snapdragon® X Elite 0.375 ms 0 - 0 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.185 ms 0 - 32 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® QCS6490 0.823 ms 0 - 2 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 0.679 ms 0 - 24 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 0.267 ms 0 - 21 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® SA8775P 0.458 ms 0 - 25 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® QCS9075 0.357 ms 0 - 2 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® QCM6690 0.846 ms 0 - 22 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 0.341 ms 0 - 34 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® SA7255P 0.679 ms 0 - 24 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® SA8295P 0.644 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 0.261 ms 0 - 23 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.138 ms 0 - 26 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Snapdragon® X2 Elite 0.224 ms 0 - 0 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Snapdragon® 8 Gen 3 Mobile 0.459 ms 0 - 35 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® QCS8275 (Proxy) 1.835 ms 0 - 26 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® QCS8550 (Proxy) 0.692 ms 0 - 1 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® SA8775P 1.018 ms 0 - 27 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® QCS9075 0.86 ms 0 - 3 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® QCS8450 (Proxy) 0.947 ms 0 - 38 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® SA7255P 1.835 ms 0 - 26 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® SA8295P 1.31 ms 0 - 25 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 0.362 ms 0 - 25 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.318 ms 0 - 29 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.184 ms 0 - 31 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® QCS6490 0.684 ms 0 - 3 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 0.702 ms 0 - 23 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 0.272 ms 0 - 2 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® SA8775P 0.472 ms 0 - 24 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® QCS9075 0.367 ms 0 - 2 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® QCM6690 0.827 ms 0 - 21 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 0.349 ms 0 - 33 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® SA7255P 0.702 ms 0 - 23 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® SA8295P 0.645 ms 0 - 20 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.15 ms 0 - 26 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.268 ms 0 - 21 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.138 ms 0 - 25 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