BEVFusion: Optimized for Qualcomm Devices

BeVFusion 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 BEVFusion 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	float	Snapdragon® X2 Elite	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 3 Mobile	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ IQ-8275	QAIRT 2.45	Download
PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	QAIRT 2.45	Download
PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ IQ-9075	QAIRT 2.45	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Mobile	QAIRT 2.45, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	QAIRT 2.45, ONNX Runtime 1.27.1	Download
QNN_CONTEXT_BINARY	float	Snapdragon® X2 Elite	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 3 Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ IQ-8275	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ IQ-9075	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® SA7255P	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 Mobile	QAIRT 2.45	Download

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

Model Details

Model Type: Model_use_case.driver_assistance

Model Stats:

Input resolution: 1 x 6 x 3 x 256 x 704
Model checkpoint: camera-only-det.pth
Model size: 171 MB
Number of parameters: 44M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
decoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® X2 Elite	7.003 ms	22 - 22 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	13.025 ms	24 - 24 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 3 Mobile	9.786 ms	15 - 22 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	13.025 ms	24 - 24 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ Q-8750	7.72 ms	13 - 21 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Mobile	7.72 ms	13 - 21 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	5.731 ms	12 - 19 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® X2 Elite	7.638 ms	5 - 5 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	13.149 ms	5 - 5 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 3 Mobile	9.763 ms	5 - 13 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	23.802 ms	4 - 9 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® SA8650P	23.802 ms	4 - 9 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® SA8255P	23.802 ms	4 - 9 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ IQ-X7181	13.149 ms	5 - 5 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ Q-8750	7.735 ms	0 - 13 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® SA7255P	92.813 ms	1 - 10 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Mobile	7.735 ms	0 - 13 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 Mobile	5.847 ms	5 - 13 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Snapdragon® X2 Elite	387.679 ms	66 - 66 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	681.883 ms	96 - 96 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 3 Mobile	530.52 ms	32 - 44 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	681.883 ms	96 - 96 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ Q-8750	437.871 ms	37 - 49 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Mobile	437.871 ms	37 - 49 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	354.546 ms	38 - 51 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Snapdragon® X2 Elite	386.445 ms	12 - 12 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	681.265 ms	12 - 12 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 3 Mobile	530.623 ms	13 - 20 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	720.121 ms	0 - 9 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Qualcomm® SA8650P	720.121 ms	0 - 9 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Qualcomm® SA8255P	720.121 ms	0 - 9 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ IQ-X7181	681.265 ms	12 - 12 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ Q-8750	432.992 ms	1 - 9 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Qualcomm® SA7255P	1074.237 ms	1 - 10 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Mobile	432.992 ms	1 - 9 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 Mobile	353.741 ms	0 - 9 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Snapdragon® X2 Elite	2437.619 ms	1058 - 1058 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	3521.274 ms	1058 - 1058 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 3 Mobile	2781.115 ms	475 - 482 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	3521.274 ms	1058 - 1058 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ Q-8750	2562.907 ms	462 - 469 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Mobile	2562.907 ms	462 - 469 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	2271.074 ms	435 - 443 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Snapdragon® X2 Elite	2436.226 ms	17 - 17 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	3431.206 ms	17 - 17 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 3 Mobile	2770.131 ms	17 - 31 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	3459.164 ms	2 - 11 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Qualcomm® SA8650P	3459.164 ms	2 - 11 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Qualcomm® SA8255P	3459.164 ms	2 - 11 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ IQ-X7181	3431.206 ms	17 - 17 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ Q-8750	2562.482 ms	6 - 15 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Qualcomm® SA7255P	5513.824 ms	17 - 26 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Mobile	2562.482 ms	6 - 15 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 Mobile	2276.994 ms	17 - 25 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Snapdragon® X2 Elite	7.874 ms	18 - 18 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	13.228 ms	19 - 19 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 3 Mobile	9.203 ms	30 - 36 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	13.228 ms	19 - 19 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ Q-8750	7.775 ms	14 - 20 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Mobile	7.775 ms	14 - 20 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	6.768 ms	13 - 20 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Snapdragon® X2 Elite	8.356 ms	19 - 19 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	12.227 ms	19 - 19 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 3 Mobile	9.081 ms	19 - 26 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	15.076 ms	18 - 23 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Qualcomm® SA8650P	15.076 ms	18 - 23 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Qualcomm® SA8255P	15.076 ms	18 - 23 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ IQ-X7181	12.227 ms	19 - 19 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ Q-8750	7.775 ms	17 - 25 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Qualcomm® SA7255P	25.332 ms	18 - 27 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Mobile	7.775 ms	17 - 25 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 Mobile	6.752 ms	17 - 25 MB	NPU

License

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

References

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.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

Other

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/BEVFusion

BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

Paper • 2205.13542 • Published May 26, 2022