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 | 182.793 ms | 2 - 2 MB | NPU |
| CenterPoint | QNN_DLC | float | Snapdragon® X Elite | 322.157 ms | 2 - 2 MB | NPU |
| CenterPoint | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 252.712 ms | 0 - 753 MB | NPU |
| CenterPoint | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 518.366 ms | 2 - 736 MB | NPU |
| CenterPoint | QNN_DLC | float | Qualcomm® QCS8275 | 920.139 ms | 2 - 451 MB | NPU |
| CenterPoint | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 335.833 ms | 2 - 4 MB | NPU |
| CenterPoint | QNN_DLC | float | Qualcomm® QCS8450 | 518.366 ms | 2 - 736 MB | NPU |
| CenterPoint | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 210.78 ms | 0 - 461 MB | NPU |
| CenterPoint | QNN_DLC | float | Qualcomm® SA8295P | 442.021 ms | 1 - 449 MB | NPU |
| CenterPoint | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 174.671 ms | 2 - 722 MB | NPU |
| CenterPoint | QNN_DLC | float | Qualcomm® SA7255P | 920.139 ms | 2 - 451 MB | NPU |
| CenterPoint | QNN_DLC | float | Qualcomm® QCS9075 | 423.202 ms | 2 - 11 MB | NPU |
| CenterPoint | QNN_DLC | float | Qualcomm® QCS8750 | 210.78 ms | 0 - 461 MB | NPU |
| CenterPoint | QNN_DLC | float | Qualcomm® QCS7181 | 322.157 ms | 2 - 2 MB | NPU |
| CenterPoint | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3854.229 ms | 1835 - 1843 MB | CPU |
| CenterPoint | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 5099.219 ms | 1858 - 1870 MB | CPU |
| CenterPoint | TFLITE | float | Qualcomm® QCS8275 | 6174.644 ms | 1848 - 1856 MB | CPU |
| CenterPoint | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 5389.073 ms | 1828 - 1836 MB | CPU |
| CenterPoint | TFLITE | float | Qualcomm® SA8775P | 5380.349 ms | 1807 - 1813 MB | CPU |
| CenterPoint | TFLITE | float | Qualcomm® SA8650P | 5380.349 ms | 1807 - 1813 MB | CPU |
| CenterPoint | TFLITE | float | Qualcomm® SA8255P | 5380.349 ms | 1807 - 1813 MB | CPU |
| CenterPoint | TFLITE | float | Qualcomm® QCS8450 | 5099.219 ms | 1858 - 1870 MB | CPU |
| CenterPoint | TFLITE | float | Snapdragon® 8 Elite Mobile | 2816.604 ms | 1853 - 1865 MB | CPU |
| CenterPoint | TFLITE | float | Qualcomm® SA8295P | 3502.138 ms | 1807 - 1813 MB | CPU |
| CenterPoint | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 805.643 ms | 1979 - 1988 MB | CPU |
| CenterPoint | TFLITE | float | Qualcomm® SA7255P | 6174.644 ms | 1848 - 1856 MB | CPU |
| CenterPoint | TFLITE | float | Qualcomm® QCS9075 | 5160.994 ms | 2362 - 2383 MB | CPU |
| CenterPoint | TFLITE | float | Qualcomm® QCS8750 | 2816.604 ms | 1853 - 1865 MB | CPU |
License
- The license for the original implementation of CenterPoint can be found here.
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.