Cao Jianfang, Zhang Zibang, Zhao Aidi
School of Computer Science & Technology, Taiyuan University of Science and Technology, Taiyuan 030024, China.
Department of Computer Science & Technology, Xinzhou Teachers University, Xinzhou 034000, China.
Comput Intell Neurosci. 2020 Dec 29;2020:6670976. doi: 10.1155/2020/6670976. eCollection 2020.
Considering the problems of low resolution and rough details in existing mural images, this paper proposes a superresolution reconstruction algorithm for enhancing artistic mural images, thereby optimizing mural images. The algorithm takes a generative adversarial network (GAN) as the framework. First, a convolutional neural network (CNN) is used to extract image feature information, and then, the features are mapped to the high-resolution image space of the same size as the original image. Finally, the reconstructed high-resolution image is output to complete the design of the generative network. Then, a CNN with deep and residual modules is used for image feature extraction to determine whether the output of the generative network is an authentic, high-resolution mural image. In detail, the depth of the network increases, the residual module is introduced, the batch standardization of the network convolution layer is deleted, and the subpixel convolution is used to realize upsampling. Additionally, a combination of multiple loss functions and staged construction of the network model is adopted to further optimize the mural image. A mural dataset is set up by the current team. Compared with several existing image superresolution algorithms, the peak signal-to-noise ratio (PSNR) of the proposed algorithm increases by an average of 1.2-3.3 dB and the structural similarity (SSIM) increases by 0.04 = 0.13; it is also superior to other algorithms in terms of subjective scoring. The proposed method in this study is effective in the superresolution reconstruction of mural images, which contributes to the further optimization of ancient mural images.
针对现有壁画图像分辨率低、细节粗糙的问题，本文提出一种用于增强艺术壁画图像的超分辨率重建算法，从而对壁画图像进行优化。该算法以生成对抗网络（GAN）为框架。首先，使用卷积神经网络（CNN）提取图像特征信息，然后将这些特征映射到与原始图像大小相同的高分辨率图像空间。最后，输出重建的高分辨率图像以完成生成网络的设计。接着，使用具有深度和残差模块的CNN进行图像特征提取，以确定生成网络的输出是否为真实的高分辨率壁画图像。具体而言，增加网络深度，引入残差模块，删除网络卷积层的批量归一化，并使用子像素卷积来实现上采样。此外，采用多种损失函数的组合以及网络模型的分阶段构建来进一步优化壁画图像。当前团队建立了一个壁画数据集。与几种现有的图像超分辨率算法相比，所提算法的峰值信噪比（PSNR）平均提高了1.2 - 3.3dB，结构相似性（SSIM）提高了0.04 - 0.13；在主观评分方面也优于其他算法。本研究中提出的方法在壁画图像的超分辨率重建中是有效的，这有助于对古代壁画图像进行进一步优化。
