Advanced search
Publication Cover
The Imaging Science Journal Volume 71, 2023 - Issue 3
Submit an article Journal homepage
381
Views
2
CrossRef citations to date
0
Altmetric
Articles

Irregular mask image inpainting based on progressive generative adversarial networks

Hong-an LiCollege of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an, People's Republic of ChinaORCID Iconhttps://orcid.org/0000-0003-1805-8430View further author information
ORCID Icon,
Liuqing HuCollege of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an, People's Republic of ChinaCorrespondence[email protected]
ORCID Iconhttps://orcid.org/0000-0002-2058-482XView further author information
ORCID Icon &
Jing ZhangCollege of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an, People's Republic of ChinaORCID Iconhttps://orcid.org/0000-0003-2494-8077View further author information
ORCID Icon
Pages 299-312 | Received 14 Dec 2022, Accepted 09 Feb 2023, Published online: 23 Feb 2023

Figures & data

Figure 1. The basic structure of GAN.

The texts in this figure are: “Training set”, “Random noise”, “Generator”, “Fake image”, “Discriminator”, “Real” and “Fake”.
Figure 1. The basic structure of GAN.

Figure 2. Diagram of channel attention module.

Figure 2. Diagram of channel attention module.

Figure 3. Diagram of spatial attention module.

Figure 3. Diagram of spatial attention module.

Figure 4. The framework of our method.

Figure 4. The framework of our method.

Figure 5. SN-PatchGAN.

Figure 5. SN-PatchGAN.

Figure 6. Adaptive consistent attention module.

Figure 6. Adaptive consistent attention module.

Figure 7. Progressive generation network.

Figure 7. Progressive generation network.

Figure 8. Comparative experimental results on the CelebA Dataset.

Figure 8. Comparative experimental results on the CelebA Dataset.

Figure 9. Comparative experimental results on the CMP Facade Dataset.

Figure 9. Comparative experimental results on the CMP Facade Dataset.

Table 1. PSNR (dB)/SSIM (%) evaluation results of different methods on the CelebA Dataset.

Table 2. PSNR (dB)/SSIM (%) evaluation results of different methods on the CMP Facade Dataset.

Figure 10. Results of ablation studies on CelebA and CMP Facade datasets.

Figure 10. Results of ablation studies on CelebA and CMP Facade datasets.

Table 3. PSNR(dB)/SSIM(%) evaluation results of the ablation study on the CelebA Dataset.

Table 4. PSNR(dB)/SSIM(%) evaluation results of the ablation study on the CMP Facade Dataset.

Reprints and Corporate Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

To request a reprint or corporate permissions for this article, please click on the relevant link below:

Order Reprints Request Corporate Permissions

Academic Permissions

Please note: Selecting permissions does not provide access to the full text of the article, please see our help page How do I view content?

Obtain permissions instantly via Rightslink by clicking on the button below:

Request Academic Permissions

If you are unable to obtain permissions via Rightslink, please complete and submit this Permissions form. For more information, please visit our Permissions help page.

Related research

People also read lists articles that other readers of this article have read.

Recommended articles lists articles that we recommend and is powered by our AI driven recommendation engine.

Cited by lists all citing articles based on Crossref citations.
Articles with the Crossref icon will open in a new tab.