IMAGE STYLIZATION BASED ON GENERATIVE ARTIFICIAL INTELLIGENCE
Authors:
1.
Kazanskiy nacional'nyy issledovatel'skiy tehnicheskiy universitet imeni A. N. Tupoleva-KAI
Russian Federation
Russian Federation
2.
Kazan National Research Technical University named after A.N. Tupolev
(Kafedra avtomatizirovannyh sistem obrabotki informacii i upravleniya)
student
Russian Federation
student
Russian Federation
3.
Kazan National Research Technical University named after A.N. Tupolev
(Institut komp'yuternyh tehnologiy i zaschity informacii, Direktor instituta)
employee
Russian Federation
employee
Russian Federation
4.
Kazanskiy nacional'nyy issledovatel'skiy tehnicheskiy universitet imeni A. N. Tupoleva-KAI
Russian Federation
Russian Federation
Type:
Article
Pages:
from 108
to 114
Status:
Published
Received:
24.12.2025
Accepted:
25.12.2025
Published:
25.12.2025
Language:
Russian
Keywords:
IMAGE PROCESSING, IMAGE STYLES, STYLE CHARACTERISTICS, IMAGE STYLIZATION, GENERATION OF STYLIZED IMAGES, GENERATIVE-ADVERSARIAL NETWORKS, IMAGE STYLIZATION QUALITY ASSESSMENTS
Abstract (English):
Currently, generative artificial intelligence technologies are being actively developed and widely implemented. These technologies are used to solve various tasks in many areas of human activity, including image stylization in digital art, design, advertising, entertainment, and other fields. Image stylization consists in the transformation of its content while maintaining the semantic structure, but with a change in the visual style set by the sample or model parameters. Various methods are used to generate images, of which neural style transfer, variational autoencoders, generative-adversarial networks and diffusion models are considered in the article. The results of their analysis showed that the best approach for creating artistically stylized images is the use of generative-adversarial networks. There are a number of such network architectures, among which Pix2Pix, CycleGAN, StyleGAN, StarGANv and UGATIT have been investigated. Their comparative analysis showed that the CycleGAN architecture best meets the requirements of the task of stylizing images in the style of a particular painter. It does not require paired data, demonstrates resilience to different image structures, and provides stable and reproducible learning. Taken together, these advantages make CycleGAN a preferred choice for building an artistic stylization system. To conduct the experiments, an image stylization system was developed, trained on a set of images with copies of artworks by Vincent Van Gogh, Claude Monet, Henri Matisse, Ivan Aivazovsky and Ilya Repin. These authors were selected based on a set of criteria: popularity, recognition of style, genre diversity and the availability of a sufficient number of digital copies of artworks. Metrics were used to evaluate the quality of image generation. To evaluate the quality of generated images, metrics such as Kernel Inception Distance, Inception Score, and Contrastive Language-Image Pretraining based cosine similarity were used. The experimental results showed that generative models demonstrate the potential to mimic common features of artistic styles. However, in order to achieve a higher level of reliability and accuracy, further research is needed to adapt them to the given styles.
Currently, generative artificial intelligence technologies are being actively developed and widely implemented. These technologies are used to solve various tasks in many areas of human activity, including image stylization in digital art, design, advertising, entertainment, and other fields. Image stylization consists in the transformation of its content while maintaining the semantic structure, but with a change in the visual style set by the sample or model parameters. Various methods are used to generate images, of which neural style transfer, variational autoencoders, generative-adversarial networks and diffusion models are considered in the article. The results of their analysis showed that the best approach for creating artistically stylized images is the use of generative-adversarial networks. There are a number of such network architectures, among which Pix2Pix, CycleGAN, StyleGAN, StarGANv and UGATIT have been investigated. Their comparative analysis showed that the CycleGAN architecture best meets the requirements of the task of stylizing images in the style of a particular painter. It does not require paired data, demonstrates resilience to different image structures, and provides stable and reproducible learning. Taken together, these advantages make CycleGAN a preferred choice for building an artistic stylization system. To conduct the experiments, an image stylization system was developed, trained on a set of images with copies of artworks by Vincent Van Gogh, Claude Monet, Henri Matisse, Ivan Aivazovsky and Ilya Repin. These authors were selected based on a set of criteria: popularity, recognition of style, genre diversity and the availability of a sufficient number of digital copies of artworks. Metrics were used to evaluate the quality of image generation. To evaluate the quality of generated images, metrics such as Kernel Inception Distance, Inception Score, and Contrastive Language-Image Pretraining based cosine similarity were used. The experimental results showed that generative models demonstrate the potential to mimic common features of artistic styles. However, in order to achieve a higher level of reliability and accuracy, further research is needed to adapt them to the given styles.
Keywords:
IMAGE PROCESSING, IMAGE STYLES, STYLE CHARACTERISTICS, IMAGE STYLIZATION, GENERATION OF STYLIZED IMAGES, GENERATIVE-ADVERSARIAL NETWORKS, IMAGE STYLIZATION QUALITY ASSESSMENTS
IMAGE PROCESSING, IMAGE STYLES, STYLE CHARACTERISTICS, IMAGE STYLIZATION, GENERATION OF STYLIZED IMAGES, GENERATIVE-ADVERSARIAL NETWORKS, IMAGE STYLIZATION QUALITY ASSESSMENTS
