bachelor thesis
Abstract
In this thesis, we tackle the issues of artificial intelligence and DeepFake
technology, which in the era of rapid digitalization, pose significant security
and privacy concerns. We focus on the assessment of quality and visual
realism of DeepFakes, a key factor for the impact of a forged video. We
introduce an effective approach for quantifying the visual realism of DeepFake
videos, using an ensemble of ConvNext, a Convolutional Neural Network
(CNN), and Eva, a vanilla Vision Transformer (ViT). These models were
trained on a subset of the DeepFake Game Competition 2022 (DFGC 2022)
dataset to regress to Mean Opinion Scores (MOS) from DeepFake videos. Our
work yielded successful results, securing third place in the DeepFake Game
Competition on Visual Realism Assessment (DFGC-VRA 2023). The thesis
provides a detailed presentation of the employed models, data preprocessing
procedures, and training, as well as a comparison of our results with other
competitors.
Keywords
deepfake videos;deepfake;visual realism;deep learning;artificial intelligence;computer and information science;diploma thesis;
Data
Language: |
English |
Year of publishing: |
2023 |
Typology: |
2.11 - Undergraduate Thesis |
Organization: |
UL FRI - Faculty of Computer and Information Science |
Publisher: |
[L. Dragar] |
UDC: |
004.85:621.397(043.2) |
COBISS: |
168011011
|
Views: |
46 |
Downloads: |
14 |
Average score: |
0 (0 votes) |
Metadata: |
|
Other data
Secondary language: |
Slovenian |
Secondary title: |
Ocena kakovosti ponarejenih posnetkov |
Secondary abstract: |
V diplomski nalogi obravnavamo problematiko umetne inteligence in tehno-
logijo globokih ponaredkov (angl. DeepFake), ki sta v dobi hitre digitalizacije
ključni za varnost in zasebnost. Osredotočili smo se na ocenjevanje kakovosti
in vizualnega realizma globoko ponarejenih videposnetkov, kar je ključnega
pomena za njihov vpliv. Predstavljamo učinkovit pristop za kvantifikacijo
vizualnega realizma globokih ponaredkov z uporabo ansambla dveh napred-
nih globokih nevronskih mrež imenovanih ConvNext in Eva. Modela smo
natrenirali na podmnožici podatkovne množice DeepFake Game Competition
(DFGC) 2022, s ciljem napovedati povprečno oceno mnenja (MOS) ponare-
jenega videoposnetka. Rezultati našega dela so se izkazali za uspešne, saj je
naš pristop na tekmovanju DFGC-VRA 2023 zasedel tretje mesto. V diplom-
ski nalogi so podrobno predstavljeni uporabljeni modeli, postopki predhodne
obdelave podatkov in treniranja modelov, ter primerjava naših rezultatov s
sotekmovalci. |
Secondary keywords: |
ponarejeni videoposnetki;kakovost;umetna inteligenca;globoki ponaredek;vizualni realizem;univerzitetni študij;diplomske naloge;Globoko učenje (strojno učenje);Ponarejanje in ponaredki;Videoposnetki;Računalništvo;Univerzitetna in visokošolska dela; |
Type (COBISS): |
Bachelor thesis/paper |
Study programme: |
1000468 |
Embargo end date (OpenAIRE): |
1970-01-01 |
Thesis comment: |
Univ. v Ljubljani, Fak. za računalništvo in informatiko |
Pages: |
58 str. |
ID: |
19929459 |