Журнал «Современная Наука»

Russian (CIS)English (United Kingdom)
 MOSCOW +7(495)-142-86-81

GENERATION OF SYNTHETIC VIDEOS ACCORDING TO THE NECESSARY PARAMETERS

Vysotsky Roman Nikolaevich  (Jewish University, Moscow)

Demichev Vasily Anatolyevich  (Docent Pskov State University, Pskov, Jewish University, Moscow )

The basic principles of operation of generative neural networks are considered using the example of developing a project for frame-by-frame video generation based on the first frame and a video sample. Using a variational autoencoder, the image is transformed into a feature space, and then a decoder is used to assemble a new image based on the sample. Additional use of a generative adversarial network allows for a significant improvement in the quality of the images created.

Keywords:neural networks, generation, video, autoencoder, discriminator.
 

Read the full article …

Citation link:
Vysotsky R. N., Demichev V. A. GENERATION OF SYNTHETIC VIDEOS ACCORDING TO THE NECESSARY PARAMETERS // Современная наука: актуальные проблемы теории и практики. Серия: Естественные и Технические Науки. -2024. -№11. -С. 51-55 DOI 10.37882/2223-2966.2024.11.07
LEGAL INFORMATION:
Reproduction of materials is permitted only for non-commercial purposes with reference to the original publication. Protected by the laws of the Russian Federation. Any violations of the law are prosecuted.
© ООО "Научные технологии"

Terms Publications

Issues of the journals (Archive)

ECONOMICS AND LAW
HUMANITIES
NATURAL AND TECHNICAL SCIENCES
COGNITION

Серия - Natural and Technical Sciences