CVT: Optimized for Qualcomm Devices

Cross-View Transformer generates real-time bird's-eye view maps from multiple vehicle cameras for autonomous driving.

This is based on the implementation of CVT 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
ONNX	float	Universal	QAIRT 2.45, ONNX Runtime 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download

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

Model Details

Model Type: Model_use_case.driver_assistance

Model Stats:

• Inference latency: RealTime
• Input resolution: 1x6x3x224x480
• Model checkpoint: vehicles_50k.pt
• Model size (float): 5.18 MB
• Number of parameters: 1.33M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
CVT	ONNX	float	Snapdragon® X2 Elite	179.834 ms	8 - 8 MB	NPU
CVT	ONNX	float	Snapdragon® X Elite	278.673 ms	20 - 20 MB	NPU
CVT	ONNX	float	Snapdragon® 8 Gen 3 Mobile	225.436 ms	8 - 2726 MB	NPU
CVT	ONNX	float	Snapdragon® 8 Gen 1 Mobile	444.226 ms	8 - 2755 MB	NPU
CVT	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	332.188 ms	0 - 2051 MB	NPU
CVT	ONNX	float	Qualcomm® QCS8450	444.226 ms	8 - 2755 MB	NPU
CVT	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	278.673 ms	20 - 20 MB	NPU
CVT	ONNX	float	Qualcomm® Dragonwing™ Q-8750	188.833 ms	3 - 2396 MB	NPU
CVT	ONNX	float	Snapdragon® 8 Elite Mobile	188.833 ms	3 - 2396 MB	NPU
CVT	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	167.698 ms	0 - 2442 MB	NPU
CVT	QNN_DLC	float	Snapdragon® X2 Elite	183.246 ms	7 - 7 MB	NPU
CVT	QNN_DLC	float	Snapdragon® X Elite	277.978 ms	7 - 7 MB	NPU
CVT	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	223.295 ms	0 - 2570 MB	NPU
CVT	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	442.247 ms	7 - 2720 MB	NPU
CVT	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	424.739 ms	2 - 2213 MB	NPU
CVT	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	334.128 ms	8 - 1657 MB	NPU
CVT	QNN_DLC	float	Qualcomm® SA8775P	292.604 ms	2 - 2213 MB	NPU
CVT	QNN_DLC	float	Qualcomm® SA8650P	292.604 ms	2 - 2213 MB	NPU
CVT	QNN_DLC	float	Qualcomm® SA8255P	292.604 ms	2 - 2213 MB	NPU
CVT	QNN_DLC	float	Qualcomm® QCS8450	442.247 ms	7 - 2720 MB	NPU
CVT	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	282.71 ms	7 - 17 MB	NPU
CVT	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	277.978 ms	7 - 7 MB	NPU
CVT	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	184.32 ms	4 - 2294 MB	NPU
CVT	QNN_DLC	float	Qualcomm® SA7255P	424.739 ms	2 - 2213 MB	NPU
CVT	QNN_DLC	float	Qualcomm® SA8295P	334.316 ms	0 - 2324 MB	NPU
CVT	QNN_DLC	float	Snapdragon® 8 Elite Mobile	184.32 ms	4 - 2294 MB	NPU
CVT	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	168.51 ms	7 - 2317 MB	NPU
CVT	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	217.652 ms	98 - 2774 MB	NPU
CVT	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	420.463 ms	1 - 2726 MB	NPU
CVT	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	323.215 ms	0 - 3 MB	NPU
CVT	TFLITE	float	Qualcomm® QCS8450	420.463 ms	1 - 2726 MB	NPU
CVT	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	182.869 ms	1 - 2364 MB	NPU
CVT	TFLITE	float	Qualcomm® SA8295P	330.821 ms	0 - 2306 MB	NPU
CVT	TFLITE	float	Snapdragon® 8 Elite Mobile	182.869 ms	1 - 2364 MB	NPU
CVT	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	167.033 ms	0 - 2315 MB	NPU

License

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

References

• Cross-view Transformers for real-time Map-view Semantic Segmentation
• 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.