## Atention-guided CNN for image denoising(ADNet)by Chunwei Tian, Yong Xu, Zuoyong Li, Wangmeng Zuo, Lunke Fei and Hong Liu is publised by Neural Networks, 2020 (https://www.sciencedirect.com/science/article/pii/S0893608019304241) and it is implemented by Pytorch.
## Absract
#### Deep convolutional neural networks (CNNs) have attracted considerable interest in low-level computer vision. Researches are usually devoted to improving the performance via very deep CNNs. However, as the depth increases, influences of the shallow layers on deep layers are weakened. Inspired by the fact, we propose an attention-guided denoising convolutional neural network (ADNet), mainly including a sparse block (SB), a feature enhancement block (FEB), an attention block (AB) and a reconstruction block (RB) for image denoising. Specifically, the SB makes a tradeoff between performance and efficiency by using dilated and common convolutions to remove the noise. The FEB integrates global and local features information via a long path to enhance the expressive ability of the denoising model. The AB is used to finely extract the noise information hidden in the complex background, which is very effective for complex noisy images, especially real noisy images and bind denoising. Also, the FEB is integrated with the AB to improve the efficiency and reduce the complexity for training a denoising model. Finally, a RB aims to construct the clean image through the obtained noise mapping and the given noisy image. Additionally, comprehensive experiments show that the proposed ADNet performs very well in three tasks (i.e. synthetic and real noisy images, and blind denoising) in terms of both quantitative and qualitative evaluations. The code of ADNet is accessible at https://github.com/hellloxiaotian/ADNet.
## Requirements (Pytorch)
#### Pytorch 0.41
#### Python 2.7
#### torchvision
#### openCv for Python
#### HDF5 for Python
## Commands
### Training
### Training datasets
#### The training dataset of the gray noisy images is downloaded at https://pan.baidu.com/s/1nkY-b5_mdzliL7Y7N9JQRQ
#### The training dataset of the color noisy images is downloaded at https://pan.baidu.com/s/1ou2mK5JUh-K8iMu8-DMcMw
### Train ADNet-S (ADNet with known noise level)
#### python train.py --prepropcess True --num_of_layers 17 --mode S --noiseL 25 --val_noiseL 25
### Train ADNet-B (DnCNN with blind noise level)
#### python train.py --preprocess True --num_of_layers 17 --mode B --val_noiseL 25
### Test
### Gray noisy images
#### python test.py --num_of_layers 17 --logdir g15 --test_data Set68 --test_noiseL 15
### Gray blind denoising
#### python test_Gb.py --num_of_layers 17 --logdir gblind --test_data Set68 --test_noiseL 25
### Color noisy images
#### python test_c.py --num_of_layers 17 --logdir g15 --test_data Set68 --test_noiseL 15
### Color blind denoising
#### python test_c.py --num_of_layers 17 --logdir cblind --test_data Set68 --test_noiseL 15
### Network architecture
![RUNOOB 图标](./networkandresult/1.png)
### Test Results
#### 1. ADNet for BSD68
![RUNOOB 图标](./networkandresult/2BSD.png)
#### 2. ADNet for Set12
![RUNOOB 图标](./networkandresult/3Set12.png)
#### 3. ADNet for CBSD68, Kodak24 and McMaster
![RUNOOB 图标](./networkandresult/4color.png)
#### 4. ADNet for CBSD68, Kodak24 and McMaster
![RUNOOB 图标](./networkandresult/5realnoisy.png)
#### 5. Running time of ADNet for a noisy image of different sizes.
![RUNOOB 图标](./networkandresult/6ruungtime.png)
#### 6. Complexity of ADNet
![RUNOOB 图标](./networkandresult/7complexity.png)
#### 7. 9 real noisy images
![RUNOOB 图标](./networkandresult/8realnoisy.png)
#### 8. 9 thermodynamic images from the proposed A
![RUNOOB 图标](./networkandresult/9ab.png)
#### 9. Visual results of BSD68
![RUNOOB 图标](./networkandresult/9gray.png)
#### 10. Visual results of Set12
![RUNOOB 图标](./networkandresult/10gray.png)
#### 11. Visual results of Kodak24
![RUNOOB 图标](./networkandresult/11.png)
#### 12. Visual results of McMaster
![RUNOOB 图标](./networkandresult/12.png)
### If you cite this paper, please the following format:
#### 1.Tian C, Xu Y, Li Z, et al. Attention-guided CNN for image denoising[J]. Neural Networks, 2020.
#### 2.@article{tian2020attention,
#### title={Attention-guided CNN for image denoising},
#### author={Tian, Chunwei and Xu, Yong and Li, Zuoyong and Zuo, Wangmeng and Fei, Lunke and Liu, Hong},
#### journal={Neural Networks},
#### year={2020},
#### publisher={Elsevier}
#### }
没有合适的资源?快使用搜索试试~ 我知道了~
ADnet进行图片去噪
共14个文件
py:11个
png:2个
md:1个
需积分: 5 0 下载量 55 浏览量
2024-03-28
16:20:58
上传
评论
收藏 594KB ZIP 举报
温馨提示
ADNet(Adaptive Denoising Network)是一种常用的图像去噪算法,专门设计用于从噪声图像中恢复出清晰、无噪声的图像。ADNet通过结合稀疏模块、特征增强模块、注意力模块以及重建模块,能够有效地去除图像中的噪声。 在ADNet中,稀疏模块利用扩张卷积和常规卷积来移除噪声,从而在性能和效率之间取得平衡。特征增强模块则通过集成全局与局部的特征信息来增强去噪模型的表达能力,提高模型的训练效率和减少复杂度。注意力模块用于提取隐藏在复杂背景中的噪声信息,对于复杂噪声图像(尤其是真实噪声图像和盲噪声)非常有效。最后,重建模块利用获得的噪声映射和输入的噪声图像来重构出清晰的图像。 使用ADNet进行图片去噪的过程大致如下:首先,将待去噪的图像输入到ADNet模型中。然后,模型通过稀疏模块、特征增强模块和注意力模块对图像进行处理,去除其中的噪声。最后,重建模块根据处理后的结果生成去噪后的清晰图像。
资源推荐
资源详情
资源评论
收起资源包目录
ADNet-master.zip (14个子文件)
gray
utils.py 3KB
test_Gb.py 2KB
dataset.py 5KB
models.py 15KB
train.py 10KB
test.py 2KB
networkandresult
12.png 302KB
11.png 264KB
color
utils.py 3KB
test_c.py 3KB
dataset.py 7KB
models.py 16KB
train.py 10KB
README.md 4KB
共 14 条
- 1
资源评论
yc1111yc
- 粉丝: 22
- 资源: 164
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功