Have a personal or library account? Click to login
Structure-guided Generative Adversarial Network for Image Inpainting Cover
By: Huan Liang,  Li Zhao and  Lei Cao  
Open Access
|Dec 2024

Figures & Tables

Figure 1.

Overall structure of the image inpainting network
Overall structure of the image inpainting network

Figure 2.

Schematic diagram of gated convolution structure
Schematic diagram of gated convolution structure

Figure 3.

Curves of Loss Functions during Model Training
Curves of Loss Functions during Model Training

Figure 4.

A partial sample of the Places2 dataset
A partial sample of the Places2 dataset

Figure 5.

A partial sample of the CelebA dataset
A partial sample of the CelebA dataset

Figure 6.

A partial sample of the Irregular mask dataset
A partial sample of the Irregular mask dataset

Figure 7.

The repair effect of each algorithm is displayed
The repair effect of each algorithm is displayed

Figure 8.

Comparison of Inpainting Results at Different Iterations during Training
Comparison of Inpainting Results at Different Iterations during Training

PSNR/SSIM for different image inpainting methods and different mask area ratios on the places2 dataset

Mask RatioPSNR/SSIM
CEPconvECOurs
1%-10%29.26/0.93730.87/0.92932.58/0.94733.89/0.961
10%-20%21.34/0.74624.62/0.88727.15/0.91628.43/0.935
20%-30%19.58/0.65821.43/0.82424.33/0.85925.58/0.878
30%-40%17.82/0.54919.32/0.75123.17/0.78223.81/0.814
40%-50%15.77/0.47517.48/0.68221.64/0.74722.04/0.763
50%-60%14.25/0.41616.44/0.61319.46/0.65120.53/0.686
Language: English
Page range: 1 - 8
Published on: Dec 31, 2024
Published by: Xi’an Technological University
In partnership with: Paradigm Publishing Services
Publication frequency: 4 issues per year

© 2024 Huan Liang, Li Zhao, Lei Cao, published by Xi’an Technological University
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.