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 (IF:9.657), 2020 (https://www.sciencedirect.com/science/article/pii/S0893608019304241) and it is implemented by Pytorch.
This paper is pushed on home page of the Nueral Networks. Also, it becomes a ESI highly cited paper. It is a contribution code of the GitHub in 2020. It is applied on a medical image company in USA. Besides, it is reported by wechat public accounts at https://mp.weixin.qq.com/s/Debh7PZSFTBtOVxpFh9yfQ and https://wx.zsxq.com/mweb/views/topicdetail/topicdetail.html?topic_id=548112815452544&group_id=142181451122&user_id=28514284588581&from=timeline.
This paper is the first paper via deep network properties for addressing image denoising with complex background.
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.
The training dataset of the gray noisy images is downloaded at https://pan.baidu.com/s/1nkY-b5_mdzliL7Y7N9JQRQ or https://drive.google.com/open?id=1_miSC9_luoUHSqMG83kqrwYjNoEus6Bj (google drive)
The training dataset of the color noisy images is downloaded at https://pan.baidu.com/s/1ou2mK5JUh-K8iMu8-DMcMw (baiduyun) or https://drive.google.com/open?id=1S1_QrP-fIXeFl5hYY193lr07KyZV8X8r (google drive)
Test dataset of Set68 is downloaded at https://drive.google.com/file/d/1_fw6EKne--LVnW0mo68RrIY-j6BKPdSp/view?usp=sharing (google drive)
Test dataset of Set12 is downloaded at https://drive.google.com/file/d/1cpQwFpNv1MXsM5bJkIumYfww8EPtlkWf/view?usp=sharing (google drive)
Test dataset of CBSD68 is downloaded at https://drive.google.com/file/d/1lxXQ_buMll_JVWxKpk5fp0jduW5F_MHe/view?usp=sharing (google drive)
Test dataset of Kodak24 is downloaded at https://drive.google.com/file/d/1F4_mv4oTXhiG-zyG9DI4OO05KqvEKhs9/view?usp=sharing (google drive)
The training dataset of real noisy images is downloaded at https://drive.google.com/file/d/1IYkR4zi76p7O5OCevC11VaQeKx0r1GyT/view?usp=sharing and https://drive.google.com/file/d/19MA-Rgfc89sW9GJHpj_QedFyo-uoS8o7/view?usp=sharing （google drive）
The test dataset of real noisy images is downloaded at https://drive.google.com/file/d/17DE-SV85Slu2foC0F0Ftob5VmRrHWI2h/view?usp=sharing (google drive)
