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® 8 Elite Gen 5 For Galaxy Mobile	QAIRT 2.50, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	QAIRT 2.50, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® X2 Elite	QAIRT 2.50, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	QAIRT 2.50, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 3 Mobile	QAIRT 2.50, ONNX Runtime 1.27.1	Download
PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ IQ-8275	QAIRT 2.50	Download
PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	QAIRT 2.50	Download
PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ IQ-9075	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite For Galaxy Mobile	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	float	Snapdragon® X2 Elite	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 3 Mobile	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ IQ-8275	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ IQ-9075	QAIRT 2.50	Download
QNN_CONTEXT_BINARY	float	Qualcomm® SA7255P	QAIRT 2.50	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® 8 Elite Gen 5 For Galaxy Mobile	5.793 ms	11 - 18 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	7.716 ms	10 - 21 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® X2 Elite	6.964 ms	22 - 22 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	13.055 ms	24 - 24 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 3 Mobile	9.91 ms	16 - 24 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	13.055 ms	24 - 24 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ Q-8750	7.716 ms	10 - 21 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	5.674 ms	5 - 13 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite For Galaxy Mobile	7.59 ms	0 - 8 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® X2 Elite	7.468 ms	5 - 5 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	13.152 ms	5 - 5 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 3 Mobile	9.87 ms	5 - 12 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	13.152 ms	5 - 5 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ Q-8750	7.59 ms	0 - 8 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	368.914 ms	38 - 51 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	449.146 ms	38 - 51 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Snapdragon® X2 Elite	400.599 ms	66 - 66 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	730.512 ms	87 - 87 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 3 Mobile	560.699 ms	32 - 45 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	730.512 ms	87 - 87 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ Q-8750	449.146 ms	38 - 51 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	369.929 ms	0 - 8 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite For Galaxy Mobile	445.022 ms	12 - 19 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Snapdragon® X2 Elite	441.318 ms	12 - 12 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	731.151 ms	12 - 12 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 3 Mobile	559.636 ms	13 - 19 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	731.151 ms	12 - 12 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ Q-8750	445.022 ms	12 - 19 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	2267.571 ms	405 - 413 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	2665.995 ms	559 - 567 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Snapdragon® X2 Elite	2434.662 ms	1058 - 1058 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	3515.802 ms	1058 - 1058 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 3 Mobile	2914.173 ms	552 - 559 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	3515.802 ms	1058 - 1058 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ Q-8750	2665.995 ms	559 - 567 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	2265.438 ms	17 - 29 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite For Galaxy Mobile	2654.205 ms	17 - 30 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Snapdragon® X2 Elite	2438.128 ms	17 - 17 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	3506.309 ms	17 - 17 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 3 Mobile	2921.008 ms	17 - 30 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	3506.309 ms	17 - 17 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ Q-8750	2654.205 ms	17 - 30 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	6.871 ms	15 - 22 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	7.84 ms	14 - 21 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Snapdragon® X2 Elite	7.882 ms	19 - 19 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	12.107 ms	19 - 19 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 3 Mobile	9.196 ms	32 - 40 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	12.107 ms	19 - 19 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Qualcomm® Dragonwing™ Q-8750	7.84 ms	14 - 21 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	6.825 ms	0 - 7 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite For Galaxy Mobile	7.858 ms	17 - 26 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Snapdragon® X2 Elite	8.629 ms	19 - 19 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	11.815 ms	19 - 19 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 3 Mobile	9.222 ms	19 - 26 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	11.815 ms	19 - 19 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Qualcomm® Dragonwing™ Q-8750	7.858 ms	17 - 26 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