| Title: | Orodja za manipulacijo videoposnetkov z nevronskimi mrežami : diplomsko delo |
|---|
| Authors: | ID Farič, Jure (Author)
ID Karakatič, Sašo (Mentor) More about this mentor...  |
|---|
| Files: |  UN_Faric_Jure_2022.pdf (1014,84 KB)
MD5: B438D0BCB3F83CEC9674EC158A088DAB
|
|---|
| Language: | Slovenian |
|---|
| Work type: | Bachelor thesis/paper |
|---|
| Typology: | 2.11 - Undergraduate Thesis |
|---|
| Organization: | FERI - Faculty of Electrical Engineering and Computer Science
|
|---|
| Abstract: | V diplomskem delu smo se ukvarjali s teoretičnim pregledom metod uporabljenih pri
generiranju globoko ponarejenih medijev in prikazu delujočega primera globoko
ponarejenega videoposnetka. Teoretično smo pregledali pristope za manipulacijo slik in
videoposnetkov z modeli generativnih nevronskih mrež, ter izdelali delujoč in realističen
primer globoko ponarejenega videoposnetka. Uporabili smo obstoječe videoposnetke z
nevronskimi mrežami in primerjali rezultate manipulacije s pravimi videoposnetki. V
praktičnem delu smo predstavili korake po katerih lahko izdelamo deepfake
videoposnetek z orodjem DeepFaceLab. |
|---|
| Keywords: | globoke nevronske mreže, globoko učenje, globoko ponarejeni videoposnetki, manipulacija slik, manipulacija videoposnetkov, diplomske naloge |
|---|
| Place of publishing: | Maribor |
|---|
| Place of performance: | Maribor |
|---|
| Publisher: | [J. Farič] |
|---|
| Year of publishing: | 2022 |
|---|
| Year of performance: | 2022 |
|---|
| Number of pages: | 1 spletni vir (1 datoteka PDF (VII, 35 f.)) |
|---|
| PID: | 20.500.12556/DKUM-83788 |
|---|
| UDC: | 004.85.032.26(043.2) |
|---|
| COBISS.SI-ID: | 141118979 |
|---|
| Publication date in DKUM: | 09.02.2023 |
|---|
| Views: | 1135 |
|---|
| Downloads: | 336 |
|---|
| Metadata: |    |
|---|
| Categories: | KTFMB - FERI
|
|---|
|
:
|
Copy citation |
|---|
| | | | Average score: | (0 votes) |
|---|
| Your score: | Voting is allowed only for logged in users. |
|---|
| Share: |  |
|---|
Hover the mouse pointer over a document title to show the abstract or click
on the title to get all document metadata. |
