Thesis Details
Automatické kolorování videa
Bachelor's Thesis
Student: Mikeska Tomáš
Academic Year: 2019/2020
Supervisor: Hradiš Michal, Ing., Ph.D.
English title
Automatic Video Colorization
Language
Czech
Abstract
This thesis deals with fully automatic colorization of video and images using convolutional neural networks. It summarizes existing approaches, architectures and several objective functions. In this thesis several neural networks with different objective functions are implemented and trained for automatic colorization. The best of them is able to colorize large diversity of scenes and is sufficient to produce coherently colorized video.
Keywords
neural networks, convolutional neural networks, automatic colorization, GAN, computer vision
Department
Degree Programme
Information Technology
Files
Status
defended, grade B
Date
8 July 2020
Reviewer
Committee
Čadík Martin, doc. Ing., Ph.D. (DCGM FIT BUT), předseda
Bařina David, Ing., Ph.D. (DCGM FIT BUT), člen
Burget Radek, doc. Ing., Ph.D. (DIFS FIT BUT), člen
Holík Lukáš, doc. Mgr., Ph.D. (DITS FIT BUT), člen
Jaroš Jiří, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Bařina David, Ing., Ph.D. (DCGM FIT BUT), člen
Burget Radek, doc. Ing., Ph.D. (DIFS FIT BUT), člen
Holík Lukáš, doc. Mgr., Ph.D. (DITS FIT BUT), člen
Jaroš Jiří, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Citation
MIKESKA, Tomáš. Automatické kolorování videa. Brno, 2020. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2020-07-08. Supervised by Hradiš Michal. Available from: https://www.fit.vut.cz/study/thesis/23058/
BibTeX
@bachelorsthesis{FITBT23058,
author = "Tom\'{a}\v{s} Mikeska",
type = "Bachelor's thesis",
title = "Automatick\'{e} kolorov\'{a}n\'{i} videa",
school = "Brno University of Technology, Faculty of Information Technology",
year = 2020,
location = "Brno, CZ",
language = "czech",
url = "https://www.fit.vut.cz/study/thesis/23058/"
}