CenterPoint: Optimized for Qualcomm Devices

CenterPoint is a LiDAR-based 3D object detection model that detects objects by predicting their centers and regressing other attributes. It is designed for high accuracy and real-time performance in autonomous driving applications.

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
QNN_DLC float Universal QAIRT 2.45 Download
TFLITE float Universal Download

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

Model Details

Model Type: Model_use_case.driver_assistance

Model Stats:

  • Model checkpoint: PointPillars
  • Input resolution: 5x20x5, 5x4, 5
  • Number of parameters: 21.8M
  • Model size: 83.3 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
CenterPoint QNN_DLC float Snapdragon® X2 Elite 185.299 ms 2 - 2 MB NPU
CenterPoint QNN_DLC float Snapdragon® X Elite 322.405 ms 2 - 2 MB NPU
CenterPoint QNN_DLC float Snapdragon® 8 Gen 3 Mobile 253.291 ms 0 - 749 MB NPU
CenterPoint QNN_DLC float Snapdragon® 8 Gen 1 Mobile 533.942 ms 2 - 737 MB NPU
CenterPoint QNN_DLC float Qualcomm® QCS8275 920.091 ms 1 - 450 MB NPU
CenterPoint QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 336.27 ms 2 - 4 MB NPU
CenterPoint QNN_DLC float Qualcomm® SA8775P 397.217 ms 1 - 703 MB NPU
CenterPoint QNN_DLC float Qualcomm® SA8650P 397.217 ms 1 - 703 MB NPU
CenterPoint QNN_DLC float Qualcomm® SA8255P 397.217 ms 1 - 703 MB NPU
CenterPoint QNN_DLC float Qualcomm® QCS8450 533.942 ms 2 - 737 MB NPU
CenterPoint QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 388.031 ms 2 - 11 MB NPU
CenterPoint QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 175.303 ms 2 - 722 MB NPU
CenterPoint QNN_DLC float Qualcomm® SA7255P 920.091 ms 1 - 450 MB NPU
CenterPoint QNN_DLC float Qualcomm® SA8295P 443.469 ms 1 - 449 MB NPU
CenterPoint QNN_DLC float Snapdragon® 8 Elite Mobile 210.364 ms 0 - 462 MB NPU
CenterPoint QNN_DLC float Qualcomm® Dragonwing™ Q-8750 210.364 ms 0 - 462 MB NPU
CenterPoint QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 322.405 ms 2 - 2 MB NPU
CenterPoint TFLITE float Snapdragon® 8 Gen 3 Mobile 4098.792 ms 1851 - 1860 MB CPU
CenterPoint TFLITE float Snapdragon® 8 Gen 1 Mobile 5627.607 ms 1837 - 1846 MB CPU
CenterPoint TFLITE float Qualcomm® QCS8275 6205.521 ms 1849 - 1856 MB CPU
CenterPoint TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 5014.262 ms 1837 - 1838 MB CPU
CenterPoint TFLITE float Qualcomm® SA8775P 5407.216 ms 1810 - 1815 MB CPU
CenterPoint TFLITE float Qualcomm® SA8650P 5407.216 ms 1810 - 1815 MB CPU
CenterPoint TFLITE float Qualcomm® SA8255P 5407.216 ms 1810 - 1815 MB CPU
CenterPoint TFLITE float Qualcomm® QCS8450 5627.607 ms 1837 - 1846 MB CPU
CenterPoint TFLITE float Qualcomm® Dragonwing™ IQ-9075 5147.069 ms 2364 - 2385 MB CPU
CenterPoint TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 839.133 ms 2003 - 2012 MB CPU
CenterPoint TFLITE float Qualcomm® SA7255P 6205.521 ms 1849 - 1856 MB CPU
CenterPoint TFLITE float Qualcomm® SA8295P 3450.647 ms 1810 - 1816 MB CPU
CenterPoint TFLITE float Snapdragon® 8 Elite Mobile 2808.061 ms 1806 - 1814 MB CPU
CenterPoint TFLITE float Qualcomm® Dragonwing™ Q-8750 2808.061 ms 1806 - 1814 MB CPU

License

  • The license for the original implementation of CenterPoint can be found here.

Community

Downloads last month

-

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