DnCNN: Optimized for Qualcomm Devices

DnCNN is a 17-layer denoising convolutional neural network that uses residual learning to remove Gaussian noise (sigma=25) from grayscale images. The network predicts the noise residual and subtracts it from the input to produce a clean image.

This is based on the implementation of DnCNN 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
ONNX	w8a8	Universal	QAIRT 2.45, ONNX Runtime 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.45	Download
QNN_DLC	w8a8	Universal	QAIRT 2.45	Download
TFLITE	float	Universal	QAIRT 2.45	Download
TFLITE	w8a8	Universal	QAIRT 2.45	Download

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

Model Details

Model Type: Model_use_case.image_editing

Model Stats:

Model checkpoint: dncnn_25
Input resolution: 256x256
Number of parameters: 555K
Model size (float): 2.12 MB
Model size (w8a8): 581 KB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
DnCNN	ONNX	float	Snapdragon® X2 Elite	4.04 ms	1 - 1 MB	NPU
DnCNN	ONNX	float	Snapdragon® X Elite	7.144 ms	0 - 0 MB	NPU
DnCNN	ONNX	float	Snapdragon® 8 Gen 3 Mobile	5.165 ms	1 - 178 MB	NPU
DnCNN	ONNX	float	Snapdragon® 8 Gen 1 Mobile	13.774 ms	1 - 179 MB	NPU
DnCNN	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	6.878 ms	1 - 4 MB	NPU
DnCNN	ONNX	float	Qualcomm® QCS8450	13.774 ms	1 - 179 MB	NPU
DnCNN	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	14.204 ms	1 - 4 MB	NPU
DnCNN	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	7.144 ms	0 - 0 MB	NPU
DnCNN	ONNX	float	Qualcomm® Dragonwing™ Q-8750	4.123 ms	0 - 143 MB	NPU
DnCNN	ONNX	float	Snapdragon® 8 Elite Mobile	4.123 ms	0 - 143 MB	NPU
DnCNN	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	3.21 ms	0 - 144 MB	NPU
DnCNN	ONNX	w8a8	Snapdragon® X2 Elite	1.037 ms	1 - 1 MB	NPU
DnCNN	ONNX	w8a8	Snapdragon® X Elite	1.869 ms	0 - 0 MB	NPU
DnCNN	ONNX	w8a8	Snapdragon® 8 Gen 3 Mobile	1.337 ms	0 - 48 MB	NPU
DnCNN	ONNX	w8a8	Snapdragon® 8 Gen 1 Mobile	2.359 ms	0 - 52 MB	NPU
DnCNN	ONNX	w8a8	Qualcomm® Dragonwing™ QCS6490	9.512 ms	0 - 3 MB	NPU
DnCNN	ONNX	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.791 ms	0 - 3 MB	NPU
DnCNN	ONNX	w8a8	Qualcomm® QCS8450	2.359 ms	0 - 52 MB	NPU
DnCNN	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-9075	1.887 ms	0 - 3 MB	NPU
DnCNN	ONNX	w8a8	Qualcomm® Dragonwing™ IQ-X7181	1.869 ms	0 - 0 MB	NPU
DnCNN	ONNX	w8a8	Qualcomm® Dragonwing™ Q-8750	1.216 ms	0 - 30 MB	NPU
DnCNN	ONNX	w8a8	Snapdragon® 8 Elite Mobile	1.216 ms	0 - 30 MB	NPU
DnCNN	ONNX	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.81 ms	0 - 32 MB	NPU
DnCNN	QNN_DLC	float	Snapdragon® X2 Elite	4.14 ms	0 - 0 MB	NPU
DnCNN	QNN_DLC	float	Snapdragon® X Elite	7.23 ms	0 - 0 MB	NPU
DnCNN	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	5.074 ms	0 - 173 MB	NPU
DnCNN	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	13.43 ms	0 - 178 MB	NPU
DnCNN	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8275	56.003 ms	0 - 141 MB	NPU
DnCNN	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	6.7 ms	0 - 49 MB	NPU
DnCNN	QNN_DLC	float	Qualcomm® SA8775P	13.888 ms	0 - 143 MB	NPU
DnCNN	QNN_DLC	float	Qualcomm® SA8650P	13.888 ms	0 - 143 MB	NPU
DnCNN	QNN_DLC	float	Qualcomm® SA8255P	13.888 ms	0 - 143 MB	NPU
DnCNN	QNN_DLC	float	Qualcomm® QCS8450	13.43 ms	0 - 178 MB	NPU
DnCNN	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	14.041 ms	2 - 4 MB	NPU
DnCNN	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	7.23 ms	0 - 0 MB	NPU
DnCNN	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	4.037 ms	0 - 144 MB	NPU
DnCNN	QNN_DLC	float	Qualcomm® SA7255P	56.003 ms	0 - 141 MB	NPU
DnCNN	QNN_DLC	float	Qualcomm® SA8295P	15.298 ms	0 - 139 MB	NPU
DnCNN	QNN_DLC	float	Snapdragon® 8 Elite Mobile	4.037 ms	0 - 144 MB	NPU
DnCNN	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 Mobile	3.046 ms	0 - 149 MB	NPU
DnCNN	QNN_DLC	w8a8	Snapdragon® X2 Elite	1.191 ms	0 - 0 MB	NPU
DnCNN	QNN_DLC	w8a8	Snapdragon® X Elite	2.007 ms	0 - 0 MB	NPU
DnCNN	QNN_DLC	w8a8	Snapdragon® 8 Gen 3 Mobile	1.338 ms	0 - 46 MB	NPU
DnCNN	QNN_DLC	w8a8	Snapdragon® 8 Gen 1 Mobile	2.355 ms	0 - 51 MB	NPU
DnCNN	QNN_DLC	w8a8	Qualcomm® Dragonwing™ QCS6490	9.399 ms	0 - 2 MB	NPU
DnCNN	QNN_DLC	w8a8	Qualcomm® Dragonwing™ QCS8275	7.555 ms	0 - 28 MB	NPU
DnCNN	QNN_DLC	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.784 ms	0 - 13 MB	NPU
DnCNN	QNN_DLC	w8a8	Qualcomm® SA8775P	1.998 ms	0 - 30 MB	NPU
DnCNN	QNN_DLC	w8a8	Qualcomm® SA8650P	1.998 ms	0 - 30 MB	NPU
DnCNN	QNN_DLC	w8a8	Qualcomm® SA8255P	1.998 ms	0 - 30 MB	NPU
DnCNN	QNN_DLC	w8a8	Qualcomm® QCS8450	2.355 ms	0 - 51 MB	NPU
DnCNN	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-9075	1.87 ms	2 - 4 MB	NPU
DnCNN	QNN_DLC	w8a8	Qualcomm® Dragonwing™ IQ-X7181	2.007 ms	0 - 0 MB	NPU
DnCNN	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-6690	38.845 ms	0 - 140 MB	NPU
DnCNN	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-7790	3.255 ms	0 - 140 MB	NPU
DnCNN	QNN_DLC	w8a8	Qualcomm® Dragonwing™ Q-8750	1.213 ms	0 - 28 MB	NPU
DnCNN	QNN_DLC	w8a8	Qualcomm® SA7255P	7.555 ms	0 - 28 MB	NPU
DnCNN	QNN_DLC	w8a8	Qualcomm® SA8295P	4.196 ms	0 - 26 MB	NPU
DnCNN	QNN_DLC	w8a8	Snapdragon® 8 Elite Mobile	1.213 ms	0 - 28 MB	NPU
DnCNN	QNN_DLC	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.805 ms	0 - 28 MB	NPU
DnCNN	QNN_DLC	w8a8	Snapdragon® 7 Gen 4 Mobile	3.255 ms	0 - 140 MB	NPU
DnCNN	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	5.204 ms	0 - 180 MB	NPU
DnCNN	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	13.878 ms	0 - 179 MB	NPU
DnCNN	TFLITE	float	Qualcomm® Dragonwing™ QCS8275	56.384 ms	0 - 142 MB	NPU
DnCNN	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	6.925 ms	0 - 2 MB	NPU
DnCNN	TFLITE	float	Qualcomm® SA8775P	14.161 ms	0 - 146 MB	NPU
DnCNN	TFLITE	float	Qualcomm® SA8650P	14.161 ms	0 - 146 MB	NPU
DnCNN	TFLITE	float	Qualcomm® SA8255P	14.161 ms	0 - 146 MB	NPU
DnCNN	TFLITE	float	Qualcomm® QCS8450	13.878 ms	0 - 179 MB	NPU
DnCNN	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	14.078 ms	0 - 4 MB	NPU
DnCNN	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	4.129 ms	0 - 144 MB	NPU
DnCNN	TFLITE	float	Qualcomm® SA7255P	56.384 ms	0 - 142 MB	NPU
DnCNN	TFLITE	float	Qualcomm® SA8295P	15.602 ms	0 - 141 MB	NPU
DnCNN	TFLITE	float	Snapdragon® 8 Elite Mobile	4.129 ms	0 - 144 MB	NPU
DnCNN	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	3.147 ms	0 - 151 MB	NPU
DnCNN	TFLITE	w8a8	Snapdragon® 8 Gen 3 Mobile	1.298 ms	0 - 47 MB	NPU
DnCNN	TFLITE	w8a8	Snapdragon® 8 Gen 1 Mobile	2.4 ms	0 - 51 MB	NPU
DnCNN	TFLITE	w8a8	Qualcomm® Dragonwing™ QCS6490	9.45 ms	0 - 3 MB	NPU
DnCNN	TFLITE	w8a8	Qualcomm® Dragonwing™ QCS8275	7.494 ms	0 - 29 MB	NPU
DnCNN	TFLITE	w8a8	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.709 ms	0 - 1 MB	NPU
DnCNN	TFLITE	w8a8	Qualcomm® SA8775P	1.976 ms	0 - 30 MB	NPU
DnCNN	TFLITE	w8a8	Qualcomm® SA8650P	1.976 ms	0 - 30 MB	NPU
DnCNN	TFLITE	w8a8	Qualcomm® SA8255P	1.976 ms	0 - 30 MB	NPU
DnCNN	TFLITE	w8a8	Qualcomm® QCS8450	2.4 ms	0 - 51 MB	NPU
DnCNN	TFLITE	w8a8	Qualcomm® Dragonwing™ IQ-9075	1.818 ms	0 - 3 MB	NPU
DnCNN	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-6690	38.941 ms	0 - 141 MB	NPU
DnCNN	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-7790	3.213 ms	0 - 141 MB	NPU
DnCNN	TFLITE	w8a8	Qualcomm® Dragonwing™ Q-8750	1.183 ms	0 - 29 MB	NPU
DnCNN	TFLITE	w8a8	Qualcomm® SA7255P	7.494 ms	0 - 29 MB	NPU
DnCNN	TFLITE	w8a8	Qualcomm® SA8295P	4.189 ms	0 - 26 MB	NPU
DnCNN	TFLITE	w8a8	Snapdragon® 8 Elite Mobile	1.183 ms	0 - 29 MB	NPU
DnCNN	TFLITE	w8a8	Snapdragon® 8 Elite Gen 5 Mobile	0.769 ms	0 - 29 MB	NPU
DnCNN	TFLITE	w8a8	Snapdragon® 7 Gen 4 Mobile	3.213 ms	0 - 141 MB	NPU

License

The license for the original implementation of DnCNN 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

Paper for qualcomm/DnCNN

Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

Paper • 1608.03981 • Published Aug 13, 2016