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 Mobile	QAIRT 2.42, ONNX Runtime 1.24.3	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® X2 Elite	QAIRT 2.42, ONNX Runtime 1.24.3	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	QAIRT 2.42, ONNX Runtime 1.24.3	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 3 Mobile	QAIRT 2.42, ONNX Runtime 1.24.3	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	QAIRT 2.42, ONNX Runtime 1.24.3	Download
PRECOMPILED_QNN_ONNX	float	Qualcomm® QCS9075	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 Mobile	QAIRT 2.45	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® QCS8550 (Proxy)	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite For Galaxy Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® SA7255P	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® SA8295P	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® QCS9075	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:

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

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 Mobile	5.733 ms	17 - 27 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Mobile	7.749 ms	10 - 17 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® X2 Elite	6.997 ms	24 - 24 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	13.162 ms	23 - 23 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	13.162 ms	23 - 23 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 3 Mobile	9.856 ms	17 - 23 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Qualcomm® QCS9075	24.715 ms	21 - 24 MB	NPU
decoder	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	7.749 ms	10 - 17 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 Mobile	5.71 ms	5 - 14 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Mobile	7.753 ms	3 - 16 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® X2 Elite	7.503 ms	5 - 5 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	13.106 ms	5 - 5 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	13.106 ms	5 - 5 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 3 Mobile	9.857 ms	5 - 12 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® QCS8550 (Proxy)	12.756 ms	5 - 6 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	23.764 ms	1 - 10 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	23.764 ms	1 - 10 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	23.764 ms	1 - 10 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® SA8295P	26.052 ms	0 - 6 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® QCS9075	24.391 ms	5 - 16 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite For Galaxy Mobile	7.753 ms	3 - 16 MB	NPU
decoder	QNN_CONTEXT_BINARY	float	Qualcomm® SA7255P	92.83 ms	1 - 10 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	347.538 ms	50 - 59 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Mobile	420.46 ms	38 - 52 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Snapdragon® X2 Elite	380.027 ms	102 - 102 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	687.25 ms	101 - 101 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	687.25 ms	101 - 101 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 3 Mobile	520.905 ms	32 - 43 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Qualcomm® QCS9075	705.643 ms	12 - 27 MB	NPU
encoder_1	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	420.46 ms	38 - 52 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 Mobile	356.441 ms	4 - 14 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Mobile	438.191 ms	12 - 25 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Snapdragon® X2 Elite	386.858 ms	12 - 12 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	676.05 ms	12 - 12 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	676.05 ms	12 - 12 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 3 Mobile	529.429 ms	13 - 20 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Qualcomm® QCS8550 (Proxy)	725.073 ms	13 - 14 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	720.211 ms	1 - 10 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	720.211 ms	1 - 10 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	720.211 ms	1 - 10 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Qualcomm® SA8295P	815.557 ms	0 - 5 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Qualcomm® QCS9075	705.324 ms	12 - 43 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite For Galaxy Mobile	438.191 ms	12 - 25 MB	NPU
encoder_1	QNN_CONTEXT_BINARY	float	Qualcomm® SA7255P	1074.149 ms	1 - 9 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	2217.099 ms	399 - 409 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Mobile	2455.256 ms	424 - 431 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Snapdragon® X2 Elite	2358.396 ms	1057 - 1057 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	3426.813 ms	1058 - 1058 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	3426.813 ms	1058 - 1058 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 3 Mobile	2720.635 ms	563 - 569 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Qualcomm® QCS9075	3598.373 ms	358 - 361 MB	NPU
encoder_2	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	2455.256 ms	424 - 431 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 Mobile	2153.487 ms	17 - 27 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Mobile	2428.72 ms	17 - 29 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Snapdragon® X2 Elite	2331.133 ms	17 - 17 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	3434.35 ms	17 - 17 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	3434.35 ms	17 - 17 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 3 Mobile	2796.086 ms	17 - 25 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Qualcomm® QCS8550 (Proxy)	3491.503 ms	17 - 18 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	3396.47 ms	16 - 27 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	3396.47 ms	16 - 27 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	3396.47 ms	16 - 27 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Qualcomm® SA8295P	3668.929 ms	1 - 12 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Qualcomm® QCS9075	3413.529 ms	17 - 644 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite For Galaxy Mobile	2428.72 ms	17 - 29 MB	NPU
encoder_2	QNN_CONTEXT_BINARY	float	Qualcomm® SA7255P	5456.982 ms	17 - 26 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	6.788 ms	31 - 41 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Mobile	7.792 ms	14 - 21 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Snapdragon® X2 Elite	7.799 ms	14 - 14 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	12.091 ms	18 - 18 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	12.091 ms	18 - 18 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 3 Mobile	9.226 ms	32 - 39 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Qualcomm® QCS9075	15.027 ms	18 - 39 MB	NPU
encoder_3	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	7.792 ms	14 - 21 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 Mobile	6.764 ms	18 - 28 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Mobile	7.713 ms	17 - 30 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Snapdragon® X2 Elite	8.348 ms	18 - 18 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	11.838 ms	18 - 18 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	11.838 ms	18 - 18 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 3 Mobile	9.165 ms	18 - 25 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Qualcomm® QCS8550 (Proxy)	12.635 ms	19 - 20 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	15.129 ms	18 - 27 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	15.129 ms	18 - 27 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	15.129 ms	18 - 27 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Qualcomm® SA8295P	15.055 ms	1 - 6 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Qualcomm® QCS9075	15.122 ms	18 - 43 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite For Galaxy Mobile	7.713 ms	17 - 30 MB	NPU
encoder_3	QNN_CONTEXT_BINARY	float	Qualcomm® SA7255P	25.324 ms	18 - 27 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