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 2.42, ONNX Runtime 1.24.3	Download
ONNX	w8a16_mixed_fp16	Universal	QAIRT 2.42, ONNX Runtime 1.24.3	Download
QNN_DLC	float	Universal	QAIRT 2.43	Download
TFLITE	float	Universal	QAIRT 2.43, TFLite 2.19.1	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:

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

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
CVT	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	183.261 ms	8 - 2259 MB	NPU
CVT	ONNX	float	Snapdragon® X2 Elite	181.596 ms	20 - 20 MB	NPU
CVT	ONNX	float	Snapdragon® X Elite	284.158 ms	18 - 18 MB	NPU
CVT	ONNX	float	Snapdragon® 8 Gen 3 Mobile	249.776 ms	8 - 2579 MB	NPU
CVT	ONNX	float	Qualcomm® QCS8550 (Proxy)	336.501 ms	0 - 25 MB	NPU
CVT	ONNX	float	Qualcomm® QCS9075	326.612 ms	7 - 10 MB	NPU
CVT	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	190.129 ms	5 - 2223 MB	NPU
CVT	ONNX	w8a16_mixed_fp16	Snapdragon® 8 Elite Gen 5 Mobile	260.79 ms	62 - 1220 MB	NPU
CVT	ONNX	w8a16_mixed_fp16	Snapdragon® X2 Elite	255.715 ms	69 - 69 MB	NPU
CVT	ONNX	w8a16_mixed_fp16	Snapdragon® X Elite	424.841 ms	70 - 70 MB	NPU
CVT	ONNX	w8a16_mixed_fp16	Snapdragon® 8 Gen 3 Mobile	365.931 ms	58 - 2557 MB	NPU
CVT	ONNX	w8a16_mixed_fp16	Snapdragon® 8 Elite For Galaxy Mobile	277.338 ms	57 - 1050 MB	NPU
CVT	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	167.529 ms	7 - 2257 MB	NPU
CVT	QNN_DLC	float	Snapdragon® X2 Elite	180.883 ms	7 - 7 MB	NPU
CVT	QNN_DLC	float	Snapdragon® X Elite	279.839 ms	7 - 7 MB	NPU
CVT	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	222.043 ms	6 - 2553 MB	NPU
CVT	QNN_DLC	float	Qualcomm® QCS8275 (Proxy)	420.185 ms	1 - 2187 MB	NPU
CVT	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	333.586 ms	7 - 10 MB	NPU
CVT	QNN_DLC	float	Qualcomm® SA8775P	291.639 ms	2 - 2187 MB	NPU
CVT	QNN_DLC	float	Qualcomm® QCS9075	323.621 ms	7 - 16 MB	NPU
CVT	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	442.643 ms	6 - 2647 MB	NPU
CVT	QNN_DLC	float	Qualcomm® SA7255P	420.185 ms	1 - 2187 MB	NPU
CVT	QNN_DLC	float	Qualcomm® SA8295P	333.101 ms	1 - 2241 MB	NPU
CVT	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	184.94 ms	7 - 2170 MB	NPU
CVT	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	181.707 ms	0 - 2244 MB	NPU
CVT	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	226.435 ms	0 - 2561 MB	NPU
CVT	TFLITE	float	Qualcomm® QCS8275 (Proxy)	425.499 ms	0 - 2194 MB	NPU
CVT	TFLITE	float	Qualcomm® QCS8550 (Proxy)	311.817 ms	0 - 4 MB	NPU
CVT	TFLITE	float	Qualcomm® SA8775P	296.258 ms	0 - 2193 MB	NPU
CVT	TFLITE	float	Qualcomm® QCS9075	326.991 ms	0 - 35 MB	NPU
CVT	TFLITE	float	Qualcomm® QCS8450 (Proxy)	461.625 ms	1 - 2670 MB	NPU
CVT	TFLITE	float	Qualcomm® SA7255P	425.499 ms	0 - 2194 MB	NPU
CVT	TFLITE	float	Qualcomm® SA8295P	337.147 ms	0 - 2230 MB	NPU
CVT	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	187.619 ms	0 - 2258 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.