Date of Award
10-18-2019
Publication Type
Master Thesis
Degree Name
M.Sc.
Department
Computer Science
Keywords
text to scene generation, 3D animation, multimedia, computer graphics, spatial relations, bounding box
Supervisor
Imran Ahmad
Rights
info:eu-repo/semantics/openAccess
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Abstract
Visual information is an integral part of our daily life. Typically, it tends to convey more information than simple textual information. A visual depiction of a textual story, as an animation or video, provides a more engaging and realistic experience and can be used in different applications. Examples of such applications include but are not limited to education, advertisement, crime scene investigation, forensic analysis of a crime, treatment of different types of mental and psychological disorders, etc. Manual 3D scene creation is a time-consuming process and requires expertise of individuals familiar with the content creation environment. Automatic scene generation using textual description and a library of developed components offers a quick and easy alternative for manual scene representation and proof of concept ideas. In this thesis, we propose a scheme for extraction of objects of interest and their spatial relationships from a user-provided textual description to create a 3D dynamic scene and animation to make it more realistic.
Recommended Citation
Kadiyala, Havish, "Dynamic Scene Creation from Text" (2019). Electronic Theses and Dissertations. 8143.
https://scholar.uwindsor.ca/etd/8143