Accesso libero

Image Inpainting Research Based on Deep Learning

Zhao Li

Zhao Li

School of Computer Science and Engineering Xi’an Technological UniversityXi’an, China
Cerca questo autore su
Sciendo|Google Scholar
Li, Zhao
 e 
Zhao Ruixia

Zhao Ruixia

School of Computer Science and Engineering Xi’an Technological UniversityXi’an, China
Cerca questo autore su
Sciendo|Google Scholar
Ruixia, Zhao
  
13 lug 2020
Image Inpainting Research Based on Deep Learning's Cover Image
INFORMAZIONI SU QUESTO ARTICOLO
Articolo precedente
Articolo Successivo
Cita
Scarica la copertina
Pubblicato online: 13 lug 2020
Pagine: 23 - 30
DOI: https://doi.org/10.21307/ijanmc-2020-013
Parole chiave
© 2020 Zhao Li et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

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
Lingua:
Inglese
Frequenza di pubblicazione:
4 volte all'anno
Argomenti della rivista:
Informatica, Informatica, altro
Feed RSS della rivista