Institutional Repository of Vilnius University
Gylio matavimo pritaikymas paveikslo stiliaus perkėlime naudojant neuroninius tinklus /
Abstract
dc:descriptionThe bachelor thesis analyses the problem of the use of depth estimation in image style transfer using neural networks. The history and variety of solutions of depth estimation is addressed and a couple of models are used together with style transfer algorithm DIA. The chosen depth estimation models are FCRN and MiDaS. Various ways to connect the models are discussed and two them are implemented. The results are analysed, conclusions are made and suggestions for future research are stated. It is determined that FCRN depth estimation network is more suitable for integration with DIA style transfer method for its more stable results conserning all types of image pairs.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2022
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Urbonavičiūtė, Raminta,
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:ELABAETD146242908&prefLang=en_US