---
title: DnCNN
canonical_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/DnCNN"
md_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/DnCNN.md"
repository: Qualcomm-AI-Hub/DnCNN
last_updated: 2026-10-16
license: mit
pipeline_tag: image-to-image
tasks:
  - image-to-image
downloads: 0
stars: 0
tags:
  - real_time
  - android
---

# DnCNN

> DnCNN - Qualcomm-AI-Hub 在 ModelScope 开源的模型。DnCNN: Optimized for Qualcomm Devices

Qualcomm-AI-Hub/DnCNN 是 ModelScope 魔搭社区上的image-to-image模型，采用 mit 许可。

- **Repository**: Qualcomm-AI-Hub/DnCNN
- **License**: mit
- **Tasks**: image-to-image
- **Tags**: real_time, android
- **Downloads**: 0
- **Stars**: 0
- **Last updated**: 2026-10-16

Source: https://www.modelscope.cn/models/Qualcomm-AI-Hub/DnCNN

---

![](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/dncnn/web-assets/model_demo.png)

# 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](https://github.com/cszn/KAIR).
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/dncnn) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).

Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.cn) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) 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](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/dncnn/releases/v0.62.1/dncnn-onnx-float.zip)
| ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/dncnn/releases/v0.62.1/dncnn-onnx-w8a8.zip)
| QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/dncnn/releases/v0.62.1/dncnn-qnn_dlc-float.zip)
| QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/dncnn/releases/v0.62.1/dncnn-qnn_dlc-w8a8.zip)
| TFLITE | float | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/dncnn/releases/v0.62.1/dncnn-tflite-float.zip)
| TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/dncnn/releases/v0.62.1/dncnn-tflite-w8a8.zip)

For more device-specific assets and performance metrics, visit **[DnCNN on Qualcomm® AI Hub](https://aihub.qualcomm.cn/models/dncnn)**.


### Option 2: Export with Custom Configurations

Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/dncnn) 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](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/dncnn) for usage instructions.

## Model Details

**Model Type:** Model_use_case.image_editing

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

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| DnCNN | ONNX | float | Snapdragon® X2 Elite | 4.043 ms | 1 - 1 MB | NPU
| DnCNN | ONNX | float | Snapdragon® X Elite | 7.157 ms | 0 - 0 MB | NPU
| DnCNN | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.147 ms | 1 - 177 MB | NPU
| DnCNN | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 13.779 ms | 1 - 178 MB | NPU
| DnCNN | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 16.075 ms | 1 - 4 MB | NPU
| DnCNN | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.864 ms | 1 - 101 MB | NPU
| DnCNN | ONNX | float | Qualcomm® QCS8450 | 13.779 ms | 1 - 178 MB | NPU
| DnCNN | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 13.987 ms | 1 - 4 MB | NPU
| DnCNN | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 7.157 ms | 0 - 0 MB | NPU
| DnCNN | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.118 ms | 0 - 142 MB | NPU
| DnCNN | ONNX | float | Snapdragon® 8 Elite Mobile | 4.118 ms | 0 - 142 MB | NPU
| DnCNN | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.204 ms | 0 - 145 MB | NPU
| DnCNN | ONNX | w8a8 | Snapdragon® X2 Elite | 1.042 ms | 1 - 1 MB | NPU
| DnCNN | ONNX | w8a8 | Snapdragon® X Elite | 1.873 ms | 0 - 0 MB | NPU
| DnCNN | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.34 ms | 0 - 48 MB | NPU
| DnCNN | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 2.361 ms | 0 - 53 MB | NPU
| DnCNN | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 9.327 ms | 0 - 3 MB | NPU
| DnCNN | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 2.211 ms | 0 - 4 MB | NPU
| DnCNN | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.792 ms | 0 - 2 MB | NPU
| DnCNN | ONNX | w8a8 | Qualcomm® QCS8450 | 2.361 ms | 0 - 53 MB | NPU
| DnCNN | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.909 ms | 0 - 3 MB | NPU
| DnCNN | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 1.873 ms | 0 - 0 MB | NPU
| DnCNN | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 40.481 ms | 2 - 145 MB | NPU
| DnCNN | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 3.262 ms | 0 - 144 MB | NPU
| DnCNN | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 1.218 ms | 0 - 34 MB | NPU
| DnCNN | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 1.218 ms | 0 - 34 MB | NPU
| DnCNN | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.811 ms | 0 - 30 MB | NPU
| DnCNN | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 3.262 ms | 0 - 144 MB | NPU
| DnCNN | QNN_DLC | float | Snapdragon® X2 Elite | 4.184 ms | 0 - 0 MB | NPU
| DnCNN | QNN_DLC | float | Snapdragon® X Elite | 7.219 ms | 0 - 0 MB | NPU
| DnCNN | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.05 ms | 0 - 173 MB | NPU
| DnCNN | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 13.44 ms | 0 - 177 MB | NPU
| DnCNN | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 15.771 ms | 0 - 3 MB | NPU
| DnCNN | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.703 ms | 0 - 2 MB | NPU
| DnCNN | QNN_DLC | float | Qualcomm® SA8775P | 13.891 ms | 0 - 143 MB | NPU
| DnCNN | QNN_DLC | float | Qualcomm® SA8650P | 13.891 ms | 0 - 143 MB | NPU
| DnCNN | QNN_DLC | float | Qualcomm® SA8255P | 13.891 ms | 0 - 143 MB | NPU
| DnCNN | QNN_DLC | float | Qualcomm® QCS8450 | 13.44 ms | 0 - 177 MB | NPU
| DnCNN | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 14.033 ms | 0 - 2 MB | NPU
| DnCNN | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 7.219 ms | 0 - 0 MB | NPU
| DnCNN | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 4.034 ms | 0 - 141 MB | NPU
| DnCNN | QNN_DLC | float | Qualcomm® SA7255P | 55.984 ms | 0 - 141 MB | NPU
| DnCNN | QNN_DLC | float | Qualcomm® SA8295P | 15.289 ms | 0 - 139 MB | NPU
| DnCNN | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 4.034 ms | 0 - 141 MB | NPU
| DnCNN | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.024 ms | 0 - 149 MB | NPU
| DnCNN | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 1.173 ms | 0 - 0 MB | NPU
| DnCNN | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.987 ms | 1 - 1 MB | NPU
| DnCNN | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.341 ms | 0 - 46 MB | NPU
| DnCNN | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 2.369 ms | 0 - 50 MB | NPU
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 9.317 ms | 0 - 2 MB | NPU
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 2.177 ms | 0 - 2 MB | NPU
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.77 ms | 0 - 14 MB | NPU
| DnCNN | QNN_DLC | w8a8 | Qualcomm® SA8775P | 2.012 ms | 0 - 30 MB | NPU
| DnCNN | QNN_DLC | w8a8 | Qualcomm® SA8650P | 2.012 ms | 0 - 30 MB | NPU
| DnCNN | QNN_DLC | w8a8 | Qualcomm® SA8255P | 2.012 ms | 0 - 30 MB | NPU
| DnCNN | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 2.369 ms | 0 - 50 MB | NPU
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.877 ms | 0 - 2 MB | NPU
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 1.987 ms | 1 - 1 MB | NPU
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 38.913 ms | 0 - 140 MB | NPU
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 3.251 ms | 0 - 140 MB | NPU
| DnCNN | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 1.207 ms | 0 - 29 MB | NPU
| DnCNN | QNN_DLC | w8a8 | Qualcomm® SA7255P | 7.585 ms | 0 - 28 MB | NPU
| DnCNN | QNN_DLC | w8a8 | Qualcomm® SA8295P | 4.238 ms | 0 - 25 MB | NPU
| DnCNN | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 1.207 ms | 0 - 29 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 | 3.251 ms | 0 - 140 MB | NPU
| DnCNN | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.192 ms | 0 - 179 MB | NPU
| DnCNN | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 13.885 ms | 0 - 179 MB | NPU
| DnCNN | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 16.049 ms | 0 - 5 MB | NPU
| DnCNN | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.933 ms | 0 - 2 MB | NPU
| DnCNN | TFLITE | float | Qualcomm® SA8775P | 14.15 ms | 0 - 145 MB | NPU
| DnCNN | TFLITE | float | Qualcomm® SA8650P | 14.15 ms | 0 - 145 MB | NPU
| DnCNN | TFLITE | float | Qualcomm® SA8255P | 14.15 ms | 0 - 145 MB | NPU
| DnCNN | TFLITE | float | Qualcomm® QCS8450 | 13.885 ms | 0 - 179 MB | NPU
| DnCNN | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 14.003 ms | 0 - 4 MB | NPU
| DnCNN | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 4.129 ms | 0 - 143 MB | NPU
| DnCNN | TFLITE | float | Qualcomm® SA7255P | 56.396 ms | 0 - 142 MB | NPU
| DnCNN | TFLITE | float | Qualcomm® SA8295P | 15.608 ms | 0 - 141 MB | NPU
| DnCNN | TFLITE | float | Snapdragon® 8 Elite Mobile | 4.129 ms | 0 - 143 MB | NPU
| DnCNN | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.17 ms | 0 - 146 MB | NPU
| DnCNN | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.304 ms | 0 - 47 MB | NPU
| DnCNN | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 2.37 ms | 0 - 51 MB | NPU
| DnCNN | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 9.406 ms | 0 - 3 MB | NPU
| DnCNN | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 2.14 ms | 0 - 3 MB | NPU
| DnCNN | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.703 ms | 0 - 2 MB | NPU
| DnCNN | TFLITE | w8a8 | Qualcomm® SA8775P | 1.985 ms | 0 - 30 MB | NPU
| DnCNN | TFLITE | w8a8 | Qualcomm® SA8650P | 1.985 ms | 0 - 30 MB | NPU
| DnCNN | TFLITE | w8a8 | Qualcomm® SA8255P | 1.985 ms | 0 - 30 MB | NPU
| DnCNN | TFLITE | w8a8 | Qualcomm® QCS8450 | 2.37 ms | 0 - 51 MB | NPU
| DnCNN | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.824 ms | 0 - 3 MB | NPU
| DnCNN | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 40.346 ms | 0 - 141 MB | NPU
| DnCNN | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 3.215 ms | 0 - 141 MB | NPU
| DnCNN | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 1.194 ms | 0 - 34 MB | NPU
| DnCNN | TFLITE | w8a8 | Qualcomm® SA7255P | 7.489 ms | 0 - 29 MB | NPU
| DnCNN | TFLITE | w8a8 | Qualcomm® SA8295P | 4.18 ms | 0 - 26 MB | NPU
| DnCNN | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 1.194 ms | 0 - 34 MB | NPU
| DnCNN | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.766 ms | 0 - 29 MB | NPU
| DnCNN | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 3.215 ms | 0 - 141 MB | NPU

## License
* The license for the original implementation of DnCNN can be found
  [here](https://github.com/cszn/KAIR/blob/master/LICENSE).

## References
* [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://arxiv.org/abs/1608.03981)
* [Source Model Implementation](https://github.com/cszn/KAIR)

## Community
* For questions or feedback, chat with our engineers in [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.cn).