NAFNet-DeBlur: Optimized for Qualcomm Devices

NAFNET is designed for lightweight real-time deblurring of images.

This is based on the implementation of NAFNet-DeBlur 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 1.25.0	Download
ONNX	w8a16	Universal	QAIRT 2.42, ONNX Runtime 1.25.0	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
QNN_DLC	w8a16	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download

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

Model Details

Model Type: Model_use_case.image_editing

Model Stats:

• Model checkpoint: NAFNet-REDS-width64
• Input resolution: 360x640
• Number of parameters: 67.89M
• Model size (float): 271.55 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
NAFNet-DeBlur	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	46.752 ms	8 - 991 MB	NPU
NAFNet-DeBlur	ONNX	float	Snapdragon® X2 Elite	50.135 ms	162 - 162 MB	NPU
NAFNet-DeBlur	ONNX	float	Snapdragon® X Elite	114.344 ms	146 - 146 MB	NPU
NAFNet-DeBlur	ONNX	float	Snapdragon® 8 Gen 3 Mobile	82.212 ms	9 - 1261 MB	NPU
NAFNet-DeBlur	ONNX	float	Qualcomm® QCS8550 (Proxy)	111.326 ms	0 - 171 MB	NPU
NAFNet-DeBlur	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	63.027 ms	8 - 928 MB	NPU
NAFNet-DeBlur	ONNX	float	Qualcomm® QCS9075	153.169 ms	8 - 53 MB	NPU
NAFNet-DeBlur	ONNX	float	Qualcomm® QCS8750	63.027 ms	8 - 928 MB	NPU
NAFNet-DeBlur	ONNX	float	Qualcomm® QCS7181	114.344 ms	146 - 146 MB	NPU
NAFNet-DeBlur	ONNX	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	49.896 ms	4 - 1202 MB	NPU
NAFNet-DeBlur	ONNX	w8a16	Snapdragon® X2 Elite	52.661 ms	211 - 211 MB	NPU
NAFNet-DeBlur	ONNX	w8a16	Snapdragon® X Elite	123.321 ms	148 - 148 MB	NPU
NAFNet-DeBlur	ONNX	w8a16	Snapdragon® 8 Gen 3 Mobile	83.717 ms	4 - 1460 MB	NPU
NAFNet-DeBlur	ONNX	w8a16	Qualcomm® QCS6490	14323.605 ms	1474 - 1492 MB	CPU
NAFNet-DeBlur	ONNX	w8a16	Qualcomm® QCS8550 (Proxy)	118.494 ms	0 - 109 MB	NPU
NAFNet-DeBlur	ONNX	w8a16	Qualcomm® QCM6690	7066.147 ms	1459 - 1480 MB	CPU
NAFNet-DeBlur	ONNX	w8a16	Snapdragon® 7 Gen 4 Mobile	6463.166 ms	1403 - 1420 MB	CPU
NAFNet-DeBlur	ONNX	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	69.946 ms	4 - 1052 MB	NPU
NAFNet-DeBlur	ONNX	w8a16	Qualcomm® QCS9075	145.941 ms	4 - 49 MB	NPU
NAFNet-DeBlur	ONNX	w8a16	Qualcomm® QCS7790	6463.166 ms	1403 - 1420 MB	CPU
NAFNet-DeBlur	ONNX	w8a16	Qualcomm® QCS8750	69.946 ms	4 - 1052 MB	NPU
NAFNet-DeBlur	ONNX	w8a16	Qualcomm® QCS7181	123.321 ms	148 - 148 MB	NPU
NAFNet-DeBlur	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	44.478 ms	0 - 991 MB	NPU
NAFNet-DeBlur	QNN_DLC	float	Snapdragon® X2 Elite	47.47 ms	3 - 3 MB	NPU
NAFNet-DeBlur	QNN_DLC	float	Snapdragon® X Elite	112.202 ms	3 - 3 MB	NPU
NAFNet-DeBlur	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	80.681 ms	3 - 1203 MB	NPU
NAFNet-DeBlur	QNN_DLC	float	Qualcomm® QCS8550 (Proxy)	109.364 ms	3 - 5 MB	NPU
NAFNet-DeBlur	QNN_DLC	float	Qualcomm® SA8775P	139.945 ms	0 - 915 MB	NPU
NAFNet-DeBlur	QNN_DLC	float	Qualcomm® SA8650P	139.945 ms	0 - 915 MB	NPU
NAFNet-DeBlur	QNN_DLC	float	Qualcomm® SA8255P	139.945 ms	0 - 915 MB	NPU
NAFNet-DeBlur	QNN_DLC	float	Qualcomm® QCS8450 (Proxy)	186.589 ms	2 - 841 MB	NPU
NAFNet-DeBlur	QNN_DLC	float	Qualcomm® SA8295P	162.508 ms	0 - 632 MB	NPU
NAFNet-DeBlur	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	63.577 ms	0 - 944 MB	NPU
NAFNet-DeBlur	QNN_DLC	float	Qualcomm® QCS9075	152.183 ms	5 - 11 MB	NPU
NAFNet-DeBlur	QNN_DLC	float	Qualcomm® QCS8750	63.577 ms	0 - 944 MB	NPU
NAFNet-DeBlur	QNN_DLC	float	Qualcomm® QCS7181	112.202 ms	3 - 3 MB	NPU
NAFNet-DeBlur	QNN_DLC	w8a16	Snapdragon® 8 Elite Gen 5 Mobile	40.146 ms	1 - 1034 MB	NPU
NAFNet-DeBlur	QNN_DLC	w8a16	Snapdragon® X2 Elite	43.299 ms	1 - 1 MB	NPU
NAFNet-DeBlur	QNN_DLC	w8a16	Snapdragon® X Elite	91.135 ms	1 - 1 MB	NPU
NAFNet-DeBlur	QNN_DLC	w8a16	Snapdragon® 8 Gen 3 Mobile	62.882 ms	0 - 1030 MB	NPU
NAFNet-DeBlur	QNN_DLC	w8a16	Qualcomm® QCS8275	192.965 ms	2 - 781 MB	NPU
NAFNet-DeBlur	QNN_DLC	w8a16	Qualcomm® QCS8550 (Proxy)	88.845 ms	2 - 5 MB	NPU
NAFNet-DeBlur	QNN_DLC	w8a16	Qualcomm® SA8775P	86.059 ms	2 - 780 MB	NPU
NAFNet-DeBlur	QNN_DLC	w8a16	Qualcomm® SA8650P	86.059 ms	2 - 780 MB	NPU
NAFNet-DeBlur	QNN_DLC	w8a16	Qualcomm® SA8255P	86.059 ms	2 - 780 MB	NPU
NAFNet-DeBlur	QNN_DLC	w8a16	Qualcomm® QCM6690	1292.196 ms	1 - 1488 MB	NPU
NAFNet-DeBlur	QNN_DLC	w8a16	Qualcomm® SA7255P	192.965 ms	2 - 781 MB	NPU
NAFNet-DeBlur	QNN_DLC	w8a16	Snapdragon® 7 Gen 4 Mobile	137.101 ms	1 - 1183 MB	NPU
NAFNet-DeBlur	QNN_DLC	w8a16	Snapdragon® 8 Elite For Galaxy Mobile	52.163 ms	1 - 934 MB	NPU
NAFNet-DeBlur	QNN_DLC	w8a16	Qualcomm® QCS9075	101.792 ms	1 - 6 MB	NPU
NAFNet-DeBlur	QNN_DLC	w8a16	Qualcomm® QCS7790	137.101 ms	1 - 1183 MB	NPU
NAFNet-DeBlur	QNN_DLC	w8a16	Qualcomm® QCS8750	52.163 ms	1 - 934 MB	NPU
NAFNet-DeBlur	QNN_DLC	w8a16	Qualcomm® QCS7181	91.135 ms	1 - 1 MB	NPU
NAFNet-DeBlur	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	46.057 ms	2 - 1076 MB	NPU
NAFNet-DeBlur	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	80.313 ms	0 - 1282 MB	NPU
NAFNet-DeBlur	TFLITE	float	Qualcomm® QCS8275	483.489 ms	3 - 1002 MB	NPU
NAFNet-DeBlur	TFLITE	float	Qualcomm® QCS8550 (Proxy)	109.824 ms	3 - 7 MB	NPU
NAFNet-DeBlur	TFLITE	float	Qualcomm® SA8775P	139.931 ms	3 - 1005 MB	NPU
NAFNet-DeBlur	TFLITE	float	Qualcomm® SA8650P	139.931 ms	3 - 1005 MB	NPU
NAFNet-DeBlur	TFLITE	float	Qualcomm® SA8255P	139.931 ms	3 - 1005 MB	NPU
NAFNet-DeBlur	TFLITE	float	Qualcomm® QCS8450 (Proxy)	206.205 ms	0 - 1003 MB	NPU
NAFNet-DeBlur	TFLITE	float	Qualcomm® SA8295P	162.481 ms	3 - 738 MB	NPU
NAFNet-DeBlur	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	63.17 ms	2 - 1033 MB	NPU
NAFNet-DeBlur	TFLITE	float	Qualcomm® QCS9075	153.064 ms	1 - 150 MB	NPU
NAFNet-DeBlur	TFLITE	float	Qualcomm® SA7255P	483.489 ms	3 - 1002 MB	NPU
NAFNet-DeBlur	TFLITE	float	Qualcomm® QCS8750	63.17 ms	2 - 1033 MB	NPU

License

• The license for the original implementation of NAFNet-DeBlur can be found here.

References

• Simple Baselines for Image Restoration
• 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.