CenterNet-3D: Optimized for Qualcomm Devices

CenterNet is a machine learning model for generating a birds eye view represenation from the sensors(cameras) mounted on a vehicle.

This is based on the implementation of CenterNet-3D 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
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X2 Elite	QAIRT 2.45, ONNX Runtime 1.25.0	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	QAIRT 2.45, ONNX Runtime 1.25.0	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	QAIRT 2.45, ONNX Runtime 1.25.0	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	QAIRT 2.45, ONNX Runtime 1.25.0	Download
PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	QAIRT 2.45, ONNX Runtime 1.25.0	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Mobile	QAIRT 2.45, ONNX Runtime 1.25.0	Download
PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	QAIRT 2.45, ONNX Runtime 1.25.0	Download
PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS9075	QAIRT 2.45, ONNX Runtime 1.25.0	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® X2 Elite	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 1 Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS8550 (Proxy)	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8775P	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8295P	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS9075	QAIRT 2.45	Download

For more device-specific assets and performance metrics, visit CenterNet-3D 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 CenterNet-3D on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.driver_assistance

Model Stats:

• Model checkpoint: ddd_3dop.pth
• Input resolution: 1 x 3 x 384 x 1280
• Number of parameters: 20.6M
• Model size: 79 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
CenterNet-3D	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X2 Elite	2044.22 ms	5 - 5 MB	NPU
CenterNet-3D	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® X Elite	2677.269 ms	58 - 58 MB	NPU
CenterNet-3D	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	2306.81 ms	3 - 10 MB	NPU
CenterNet-3D	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Gen 1 Mobile	4459.106 ms	3 - 12 MB	NPU
CenterNet-3D	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	3013.571 ms	1 - 63 MB	NPU
CenterNet-3D	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS8450	4459.106 ms	3 - 12 MB	NPU
CenterNet-3D	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2757.461 ms	1 - 14 MB	NPU
CenterNet-3D	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS9075	2862.9 ms	0 - 6 MB	NPU
CenterNet-3D	PRECOMPILED_QNN_ONNX	w8a16	Snapdragon® 8 Elite Mobile	2345.982 ms	3 - 15 MB	NPU
CenterNet-3D	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS8750	2345.982 ms	3 - 15 MB	NPU
CenterNet-3D	PRECOMPILED_QNN_ONNX	w8a16	Qualcomm® QCS7181	2677.269 ms	58 - 58 MB	NPU
CenterNet-3D	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X2 Elite	1984.766 ms	3 - 3 MB	NPU
CenterNet-3D	QNN_CONTEXT_BINARY	w8a16	Snapdragon® X Elite	2724.888 ms	3 - 3 MB	NPU
CenterNet-3D	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 3 Mobile	2301.691 ms	3 - 11 MB	NPU
CenterNet-3D	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Gen 1 Mobile	4429.547 ms	3 - 12 MB	NPU
CenterNet-3D	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS8275	3846.296 ms	3 - 10 MB	NPU
CenterNet-3D	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS8550 (Proxy)	3007.132 ms	28 - 31 MB	NPU
CenterNet-3D	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS8450	4429.547 ms	3 - 12 MB	NPU
CenterNet-3D	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	2741.256 ms	2 - 10 MB	NPU
CenterNet-3D	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA7255P	3846.296 ms	3 - 10 MB	NPU
CenterNet-3D	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS9075	2863.252 ms	3 - 8 MB	NPU
CenterNet-3D	QNN_CONTEXT_BINARY	w8a16	Snapdragon® 8 Elite Mobile	2343.794 ms	3 - 16 MB	NPU
CenterNet-3D	QNN_CONTEXT_BINARY	w8a16	Qualcomm® SA8295P	3466.379 ms	0 - 6 MB	NPU
CenterNet-3D	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS8750	2343.794 ms	3 - 16 MB	NPU
CenterNet-3D	QNN_CONTEXT_BINARY	w8a16	Qualcomm® QCS7181	2724.888 ms	3 - 3 MB	NPU

License

• The license for the original implementation of CenterNet-3D can be found here.

References

• Objects as Points
• 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.