To obtain access to full text of journal and articles you must register!
- Article name
- Generating photorealistic images using generative adversarial networks
- Authors
- Zhilenkov A. A., , zhilenkovanton@gmail.com, St. Petersburg State Marine Technical University, St. Petersburg, Russia
Antipov N. A., , antipovnikandr@smtu.ru, Saint-Petersburg State Marine Technical University, St. Petersburg, Russia
- Keywords
- generative adversarial network / machine learning / image generation / autoencoder
- Year
- 2024 Issue 2 Pages 12 - 16
- Code EDN
- HMSXKL
- Code DOI
- 10.52190/2073-2600_2024_2_12
- Abstract
- An overview of the current state of research in the field of generating photorealistic images is given, the basic principles of image generation are considered, a number of methods for generating photorealistic images, the principles of operation of autoencoders and variational autoencoders are described. Particular attention is paid to the use of generative adversarial networks for generating photorealistic images. The elements of generative adversarial networks are discussed in detail: their architecture, generator and discriminator, as well as loss functions. Based on the results of the consideration, a diagram of the operation of generative adversarial networks is presented. In conclusion, a number of shortcomings of generative adversarial networks are considered, the solution of which may be the direction of further research.
- Text
- BUY for read the full text of article
- Buy
- 500.00 rub
