scholarly journals VIRTUAL RESTORATION OF MISSING PAINT LOSS OF MURAL BASED ON GENERATIVE ADVERSARIAL NETWORK

Author(s):  
Q. Wang ◽  
M. Hou ◽  
S. Lyu

Abstract. Mural painting is one of the important cultural heritage reflecting the historical migration of the nation. In order to inherit these precious historical and cultural heritage, how to non - destructively and digitally protect and restore the existing murals has become an urgent task. The use of computer - assisted restoration of murals can not only save manpower and material resources, but also avoid secondary damage to the murals.However, most of the existing computer-assisted mural restoration algorithms use similar blocks with priority calculations and matching blocks in adjacent areas to guide mural restoration. There are some problems such as incoherent overall semantic structure, unnatural detail texture and inability to effectively repair large area missing remain to be solved. Aiming at the problems existing in the restoration of large area diseases such as paint loss and color fading in murals, we constructed a fine image restoration network model which based on generative adversarial network. A multi-scale dense matching repair network based on a generative adversarial network is constructed. First, the dense combination of dilated convolutions is used to improve the repair effect of detailed textures, Then, mean absolute Error, (Visual Geometry Group, VGG) feature matching, auto-guided regression, and geometric alignment are used as the loss function to guide the training of the generative network. Second, the discriminator with local and global branches is used to train the discriminant network, so that the repaired image is in the local and global content. Experiments were performed on the three mural data sets one by one. The results show that the network model can effectively restore the lines and faces in the murals. The images restored are not only coherent in semantic details, but also natural in color, which is conducive to the appreciation and display of murals. Thus, as one of the important directions of cultural heritage digital protection,the use of generative adversarial network in the digital restoration of ancient murals have been proved to be effective. It not only provides a reference for the true restoration of the murals but also means a lot to the preservation of murals.

2020 ◽  
Vol 16 (3) ◽  
pp. 555-563 ◽  
Author(s):  
Xin Yang ◽  
Wei-dong Xu ◽  
Qi Jia ◽  
Ling Li ◽  
Wan-nian Zhu ◽  
...  

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Yi Gu ◽  
Qiankun Zheng

Background. The generation of medical images is to convert the existing medical images into one or more required medical images to reduce the time required for sample diagnosis and the radiation to the human body from multiple medical images taken. Therefore, the research on the generation of medical images has important clinical significance. At present, there are many methods in this field. For example, in the image generation process based on the fuzzy C-means (FCM) clustering method, due to the unique clustering idea of FCM, the images generated by this method are uncertain of the attribution of certain organizations. This will cause the details of the image to be unclear, and the resulting image quality is not high. With the development of the generative adversarial network (GAN) model, many improved methods based on the deep GAN model were born. Pix2Pix is a GAN model based on UNet. The core idea of this method is to use paired two types of medical images for deep neural network fitting, thereby generating high-quality images. The disadvantage is that the requirements for data are very strict, and the two types of medical images must be paired one by one. DualGAN model is a network model based on transfer learning. The model cuts the 3D image into multiple 2D slices, simulates each slice, and merges the generated results. The disadvantage is that every time an image is generated, bar-shaped “shadows” will be generated in the three-dimensional image. Method/Material. To solve the above problems and ensure the quality of image generation, this paper proposes a Dual3D&PatchGAN model based on transfer learning. Since Dual3D&PatchGAN is set based on transfer learning, there is no need for one-to-one paired data sets, only two types of medical image data sets are needed, which has important practical significance for applications. This model can eliminate the bar-shaped “shadows” produced by DualGAN’s generated images and can also perform two-way conversion of the two types of images. Results. From the multiple evaluation indicators of the experimental results, it can be analyzed that Dual3D&PatchGAN is more suitable for the generation of medical images than other models, and its generation effect is better.


2019 ◽  
Vol 19 (08) ◽  
pp. 1950092 ◽  
Author(s):  
Jiecheng Xiong ◽  
Jun Chen

Severe vibrations may occur on slender structures like footbridges and cantilever stands due to human-induced loads such as walking, jumping or bouncing. Currently, to develop a load model for structural design, the main features, such as periodicity and stationarity of experimental load records, are artificially extracted and then mathematically modeled. Different physical features have been included in different load models, i.e. no unified load model exists for different individual activities. The recently emerged generative adversarial networks can be used to model high-dimensional random variables. The probability distribution of these variables learned from real samples can be used to generate new samples, avoiding extracting features artificially. In this paper, a new model is proposed which combines the conditional generative adversarial networks and Wasserstein generative adversarial networks with gradient penalty to generate individual walking, jumping and bouncing loads. The generator of the model has five fully connected layers and a one-dimensional convolutional layer, and the discriminator has five fully connected layers. After one million training steps using the experimental records, the generator can generate high-quality samples similar to real samples in waveform. Finally, by comparing the power spectral densities and single degree of freedom system’s responses of the generated samples with real samples, it is further proved that the proposed generative adversarial network model can be used to simulate various human-induced loads. Source code of the model along with its trained weights is provided to the readers to further analysis and application.


Sign in / Sign up

Export Citation Format

Share Document