Acceso abierto

Research on Style Migration Techniques Based on Generative Adversarial Networks in Chinese Painting Creation

Ying Liu

Ying Liu

School of Art and Design, Changsha University of Science and TechnologyChangsha, China
Buscar este autor en
Sciendo|Google Scholar
Liu, Ying
, 
Lin Liu

Lin Liu

School of Elementary Education, Hunan First Normal UniversityChangsha, China
Buscar este autor en
Sciendo|Google Scholar
Liu, Lin
 y 
Zheqing Liu

Zheqing Liu

Frontier Interdisciplinary College, Hunan University of Technology and BusinessChangsha, China
Buscar este autor en
Sciendo|Google Scholar
Liu, Zheqing
  
24 mar 2025
Research on Style Migration Techniques Based on Generative Adversarial Networks in Chinese Painting Creation's Cover Image
Acerca de este artículo
Artículo anterior
Artículo siguiente
Cite
Descargar portada
Publicado en línea: 24 mar 2025
Recibido: 07 nov 2024
Aceptado: 05 feb 2025
DOI: https://doi.org/10.2478/amns-2025-0781
Palabras clave
© 2025 Ying Liu et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

CycleGAN Model network internal structure
CycleGAN Model network internal structure

Figure 2.

Improved generator structure
Improved generator structure

Figure 3.

Student evaluations of the five algorithms
Student evaluations of the five algorithms

Figure 4.

Expert evaluation of the results of the four algorithms
Expert evaluation of the results of the four algorithms

Number of content samples in dataset

Object Train Set Test set Seen Unseen
Horse 1465 165 √
Shrimp 525 110 √
Cattle × 205 √
Dog × 835 √
Cat × 1115 √
Bird × 170 √
Tiger × 530 √
Lion × 445 √
Zebra × 110 √

Quantitative evaluation results of FID, SSIM and Kernel MMD

Gatys AdaIN CycleGAN CartoonGAN ChiGAN ICycleGAN
FID↓ 296.2014 224.5274 217.0988 252.3054 234.88873 180.0012
SSIM↑ 0.8719 0.9002 0.8107 0.8827 0.8791 0.9119
Kernel MMD↓ 1.085 1.0275 0.9846 1.1352 1.1045 0.9502

The details of the SWAN

Networks Operation Kernel size Stride Padding Feature maps Normalization Nonlinearity
Content Encoder Convolution 6 1 - 64 IN ReLU
Convolution 3 1 1 128 ReLU ReLU
Convolution 4 3 1 256 ReLU ReLU
Style Encoder Convolution 6 1 - 64 ReLU ReLU
Convolution 3 1 1 128 ReLU ReLU
Convolution 4 3 1 256 ReLU ReLU
Resnet Blocks Convolution 4 1 - 258 ReLU ReLU
Convolution 4 1 - 258 ReLU -
Decoder Convolution 4 3 1 128 ReLU ReLU
Convolution 4 3 1 64 ReLU ReLU
Convolution 6 2 - 3 - -
Idioma:
Inglés
Calendario de la edición:
1 veces al año
Temas de la revista:
Ciencias de la vida, Ciencias de la vida, otros, Matemáticas, Matemáticas aplicadas, Matemáticas generales, Física, Física, otros
RSS Feed de revista