Have a personal or library account? Click to login
Image Inpainting Research Based on Deep Learning Cover

Image Inpainting Research Based on Deep Learning

International Journal of Advanced Network, Monitoring and Controls
Volume 5 (2022): Issue 2 (January 2022)
By:
Zhao Li and  Zhao Ruixia  
Open Access
|Jul 2020

Figures & Tables

Figure 1.

Data flow diagram of GAN
Data flow diagram of GAN

Figure 2.

Residual structure of the encoder
Residual structure of the encoder

Figure 3.

Encoder network structure
Encoder network structure

Figure 4.

Decoding residual block network structure
Decoding residual block network structure

Figure 5.

Generate network structure diagram
Generate network structure diagram

Figure 6.

Discriminant network structure diagram
Discriminant network structure diagram

Figure 7.

Inpainting result of intermediate masked
Inpainting result of intermediate masked

Figure 8.

Inpainting result of random masked
Inpainting result of random masked

EVALUATION RESULTS OF PSNR AND SSIM METHODS

Image inpainting modelPSNRSSIM
CE[13]18.720.843
GL[14]19.900.836
Gntlpt[15]20.380.855
GMCNN[16]20.620.851
Ours24.060.857
DOI: https://doi.org/10.21307/ijanmc-2020-013 | Journal eISSN: 2470-8038
Journal RSS Feed
Language: English
Page range: 23 - 30
Published on: Jul 13, 2020
Published by: Sciendo
In partnership with: Paradigm Publishing Services
Publication frequency: 4 times per year
Keywords:
Image Inpainting,
Generation Adversarial Networks,
Residual Network,
Patch
Related subjects:
Computer sciences,
Computer sciences, other

© 2020 Zhao Li, Zhao Ruixia, published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 License.

Previous articleVolume 5 (2022): Issue 2 (January 2022)Next article