<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Tomb murals are the special kind of murals that are buried underground. Due to the narrow exit of the tomb passage, the tomb murals were excavated by dividing the whole mural into blocks, which made lots of information missing between the blocks. The digital restoration technology Image inpainting uses the edge information around the missing parts to spread the information inside of the defect area and fills the information from the outside to the inside. But it is not suitable for filling the missing parts between the tomb mural blocks. Because these parts are large for exemplar-based inpainting which may make texture dislocation and for PDE which may make cartoon blur. It is a need to generate the information outwards to complete the information. The generative adversarial network uses deep learning training by the murals remains to generate the information from inside to outside, but the typical GAN doesn‘t have a good nonlinear feature. This paper provided a generating technology based on the deep convolution generative adversarial network to rebuild the missing information between the tomb mural blocks. It built the training data set of the simulation platform with Keras and designed a whole mural generation scheme based on DCGAN. In order to get better generated results to avoid the bad artifacts; it adds the nonlinear layers by choosing 13 layers convolution and 2 deconvolution layers of the generator and contained 5 layers convolution discriminator; it designed a new phased nonlinear loss function by using Pycharm pretreatment for Numpy array file data sets; finally, it completed the generate tomb mural information to obtain the good simulation effect.</p>
</abstract>

Tomb murals are the special kind of murals that are buried underground. Due to the narrow exit of the tomb passage, the tomb murals were excavated by dividing the whole mural into blocks, which made lots of information missing between the blocks. The digital restoration technology Image inpainting uses the edge information around the missing parts to spread the information inside of the defect area and fills the information from the outside to the inside. But it is not suitable for filling the missing parts between the tomb mural blocks. Because these parts are large for exemplar-based inpainting which may make texture dislocation and for PDE which may make cartoon blur. It is a need to generate the information outwards to complete the information. The generative adversarial network uses deep learning training by the murals remains to generate the information from inside to outside, but the typical GAN doesn‘t have a good nonlinear feature. This paper provided a generating technology based on the deep convolution generative adversarial network to rebuild the missing information between the tomb mural blocks. It built the training data set of the simulation platform with Keras and designed a whole mural generation scheme based on DCGAN. In order to get better generated results to avoid the bad artifacts; it adds the nonlinear layers by choosing 13 layers convolution and 2 deconvolution layers of the generator and contained 5 layers convolution discriminator; it designed a new phased nonlinear loss function by using Pycharm pretreatment for Numpy array file data sets; finally, it completed the generate tomb mural information to obtain the good simulation effect.

Nonlinear optimization generating the Tomb Mural Blocks by GANS

School of Information and Control Engineering

Xi’an University of Architecture and Technology

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

{"article-title":"Nonlinear optimization generating the Tomb Mural Blocks by GANS"}

Tomb murals are the special kind of murals that are buried underground. Due to the narrow exit of the tomb passage, the tomb murals were excavated by dividing...

Nonlinear optimization generating the Tomb Mural Blocks by GANS

Online veröffentlicht: 31. Dez. 2020

Seitenbereich: 43 - 56

Eingereicht: 25. Sept. 2020

Akzeptiert: 02. Dez. 2020

DOI: https://doi.org/10.2478/amns.2020.2.00072

Schlüsselwörter
nonlinear optimization, tomb mural, generative adversarial network, loss function

© 2021 Meng Wu et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Nonlinear optimization generating the Tomb Mural Blocks by GANS

Online veröffentlicht: 31. Dez. 2020

Seitenbereich: 43 - 56

Eingereicht: 25. Sept. 2020

Akzeptiert: 02. Dez. 2020

DOI: https://doi.org/10.2478/amns.2020.2.00072

Schlüsselwörternonlinear optimization, tomb mural, generative adversarial network, loss function

© 2021 Meng Wu et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
nonlinear optimization, tomb mural, generative adversarial network, loss function