National Repository of Grey Literature 2 records found  Search took 0.00 seconds. 
Creating 3D Diorama from Single Image with Deep Learning
Vejbora, Martin ; Šikudová, Elena (advisor) ; Holeňa, Martin (referee)
The goal of this thesis is to automate the process of generating 3D dio- rama scenes from a single image. After an extensive analysis of existing approaches, we propose to combine the output of deep learning models for panoptic segmentation and monocular depth estimation. We encountered some limitations of the available depth model for our use case, which we addressed through fine-tuning. To construct the diorama, we separate the objects identified by segmentation into distinct images with transparent back- grounds. These images are placed in a 3D scene, arranged in a way that reflects the estimated depth of each object. We implemented our method as an add-on for Blender. The thesis was developed in collaboration with a company called polygoniq.
Carty - Arcade Racing Game
Vejbora, Martin ; Ježek, Pavel (advisor) ; Gemrot, Jakub (referee)
The goal of this thesis is to implement an arcade racing game using the Unity en- gine. Our game contains usual features of the games of this genre. These are simple and forgiving car controlling, various singleplayer modes, power ups and a split-screen multiplayer. On top of that we have created a built-in editor where players can build cars and then race with them. Players can build new cars either from prepared parts or they can import their own 3D models. We have prepared a simple Unity project with editor extension for creating of new parts. 1

Interested in being notified about new results for this query?
Subscribe to the RSS feed.