Zhang Jiahong, Zhu Yonggui, Yu Wenshu, Ma Jingning
The State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing 100024, China.
The School of Data Science and Media Intelligence, Communication University of China, Beijing 100024, China.
Sensors (Basel). 2023 Jun 26;23(13):5915. doi: 10.3390/s23135915.
Recently, convolutional neural networks (CNNs) have been widely used in image denoising, and their performance has been enhanced through residual learning. However, previous research mostly focused on optimizing the network architecture of CNNs, ignoring the limitations of the commonly used residual learning. This paper identifies two of its limitations, which are the neglect of image information and the lack of effective consideration of image self-similarity. To solve these limitations, this paper proposes a compositional denoising network (CDN), which contains two sub-paths, the image information path (IIP) and the noise estimation path (NEP), respectively. IIP is trained via an image-to-image method to extract image information. For NEP, it utilizes image self-similarity from the perspective of training. This similarity-based training method constrains NEP to output similar estimated noise distributions for different image patches with a specific kind of noise. Finally, image information and noise distribution information are comprehensively considered for image denoising. Experimental results indicate that CDN outperforms other CNN-based methods in both synthetic and real-world image denoising, achieving state-of-the-art performance.
最近，卷积神经网络（CNN）已被广泛应用于图像去噪，并且通过残差学习提高了其性能。然而，以往的研究大多集中在优化CNN的网络架构上，而忽略了常用残差学习的局限性。本文指出了其两个局限性，即对图像信息的忽视和对图像自相似性缺乏有效考虑。为了解决这些局限性，本文提出了一种组合去噪网络（CDN），它包含两个子路径，分别是图像信息路径（IIP）和噪声估计路径（NEP）。IIP通过图像到图像的方法进行训练以提取图像信息。对于NEP，它从训练的角度利用图像自相似性。这种基于相似性的训练方法约束NEP为具有特定噪声的不同图像块输出相似的估计噪声分布。最后，综合考虑图像信息和噪声分布信息进行图像去噪。实验结果表明，CDN在合成图像和真实世界图像去噪方面均优于其他基于CNN的方法，达到了当前的最优性能。
