Institutional Repository of Vilnius University
Generatyviniai besivaržantys neuroniniai tinklai 3D modeliams generuoti iš 2D nuotraukų /
Abstract
dc:descriptionA literature review is performed and an artificial intelligence based method is implemented, which, using generative adversarial networks (GAN), would be able to construct three-dimensional representations of objects captured in a photograph. Traditional three-dimensional digitization methods, general GAN theory, various improvements to GAN methods, current work on three dimensional digitization with the help of GAN, and methods for smoothing and improving the quality of 3D models are reviewed. Finally, the application and results of the analyzed methods are described.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Bieliauskas, Marius,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD192827592&prefLang=en_US