| Abstract [eng] |
A 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. |
