See the published version of this preprint at Heritage Science.
This is a preprint, a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
A new preprint design is coming!
We have improved readability, clarity, accessibility, and opportunities for engagement.
Research article
Honghai Chen
Northwest University
Corresponding Author
License:
This work is licensed under a CC BY 4.0 License. Read Full License
It has been 40 years since the reform and opening up of Shenzhen. However, there are many ancient murals hidden in the modern city. Murals are important resources that allow us to explore local history and culture. In order to better preserve and restore ancient murals, we propose a generator–discriminator network model based on an artificial intelligence algorithm. For non-structural damaged murals, the generator network method in deep learning can automatically generate the missing parts of a mural that are similar to salt-and-pepper noise. The generated image is sent to the discriminator network, which is used to determine whether the input image was generated through the generator network or was a real image. When the discriminator has significant difficulty distinguishing between the real image and the image generated by the generator network, it can be considered that the image has been well repaired by the generator network. Based on the available data, 137 mural images were selected for model training, and 22 mural images were used to observe the restoration effect of the real mural after model training. From the experimental results, the proposed algorithm has a good repair effect on the point-like damaged murals, but has a poor repair effect on murals with serious structural damage. This latter finding is due to the limited research data. Nonetheless, the algorithm can still guide restoration workers in mural repair.
Keywords
Mural restoration, Mural in Bao'an District, Generator network, Discriminator network.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
The full text of this article is available to read as a PDF.
This is a list of supplementary files associated with this preprint. Click to download.
Loading...
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Published
View the published article at Heritage Science.
No community comments so far
Editorial decision: Accept
On 21 Dec, 2020
Review #1 received
Received 02 Dec, 2020
Reviewer #2 agreed
On 29 Nov, 2020
Reviewer #1 agreed
On 29 Nov, 2020
Reviewers invited
Invitations sent on 28 Nov, 2020
Editor assigned
On 26 Nov, 2020
Submission checks complete
On 26 Nov, 2020
Editor invited
On 26 Nov, 2020
Version 1
Posted 27 Jul, 2020
No comments provided
Editorial decision: Major revision
On 30 Aug, 2020
Review #2 received
Received 28 Aug, 2020
Reviewer #2 agreed
On 13 Aug, 2020
Review #1 received
Received 31 Jul, 2020
Reviewer #1 agreed
On 28 Jul, 2020
Reviewers invited
Invitations sent on 27 Jul, 2020
Editor assigned
On 24 Jul, 2020
First submitted
On 23 Jul, 2020
Submission checks complete
On 23 Jul, 2020
Editor invited
On 23 Jul, 2020
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Learn more about our company.
A new preprint design is coming!
We have improved readability, clarity, accessibility, and opportunities for engagement.
See the published version of this preprint at Heritage Science.
This is a preprint, a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
Research article
Honghai Chen
Northwest University
Corresponding Author
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Published
View the published article at Heritage Science.
No community comments so far
Editorial decision: Accept
On 21 Dec, 2020
Review #1 received
Received 02 Dec, 2020
Reviewer #2 agreed
On 29 Nov, 2020
Reviewer #1 agreed
On 29 Nov, 2020
Reviewers invited
Invitations sent on 28 Nov, 2020
Editor assigned
On 26 Nov, 2020
Submission checks complete
On 26 Nov, 2020
Editor invited
On 26 Nov, 2020
Version 1
Posted 27 Jul, 2020
No comments provided
Editorial decision: Major revision
On 30 Aug, 2020
Review #2 received
Received 28 Aug, 2020
Reviewer #2 agreed
On 13 Aug, 2020
Review #1 received
Received 31 Jul, 2020
Reviewer #1 agreed
On 28 Jul, 2020
Reviewers invited
Invitations sent on 27 Jul, 2020
Editor assigned
On 24 Jul, 2020
First submitted
On 23 Jul, 2020
Submission checks complete
On 23 Jul, 2020
Editor invited
On 23 Jul, 2020
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
License:
This work is licensed under a CC BY 4.0 License. Read Full License
View the published article at Heritage Science.
It has been 40 years since the reform and opening up of Shenzhen. However, there are many ancient murals hidden in the modern city. Murals are important resources that allow us to explore local history and culture. In order to better preserve and restore ancient murals, we propose a generator–discriminator network model based on an artificial intelligence algorithm. For non-structural damaged murals, the generator network method in deep learning can automatically generate the missing parts of a mural that are similar to salt-and-pepper noise. The generated image is sent to the discriminator network, which is used to determine whether the input image was generated through the generator network or was a real image. When the discriminator has significant difficulty distinguishing between the real image and the image generated by the generator network, it can be considered that the image has been well repaired by the generator network. Based on the available data, 137 mural images were selected for model training, and 22 mural images were used to observe the restoration effect of the real mural after model training. From the experimental results, the proposed algorithm has a good repair effect on the point-like damaged murals, but has a poor repair effect on murals with serious structural damage. This latter finding is due to the limited research data. Nonetheless, the algorithm can still guide restoration workers in mural repair.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
The full text of this article is available to read as a PDF.
This is a list of supplementary files associated with this preprint. Click to download.
Loading...