In the project, you will gain practical experience with style generative adversarial network (StyleGAN) [see References], apply neural networks, and computational approaches to produce faces and objects transformations.
References:
This Person Does Not Exist https://thispersondoesnotexist.com
Animate your family photos https://www.myheritage.com/deep-nostalgia
Microsoft Face Demo https://azure.microsoft.com/en-us/services/cognitive-services/face
AI Makes Near-Perfect DeepFakes in 40 Seconds! https://www.youtube.com/watch?v=iXqLTJFTUGc
Two Minute Papers: 3 New Things An AI Can Do With Your Photos! https://youtu.be/B8RMUSmIGCI
Two Minute Papers: Everybody Can Make Deepfakes Now! https://youtu.be/mUfJOQKdtAk
Arxiv Insights: Face editing with Generative Adversarial Networks https://youtu.be/dCKbRCUyop8
Henry AI Labs: StyleGAN https://youtu.be/AQBti_wN414
NVidia just released StyleGAN 2 https://youtu.be/BIZg_PPuj_0
When A.I. Becomes Creative https://youtu.be/KZ7BnJb30Cc
GitHub: OpenFace https://github.com/TadasBaltrusaitis/OpenFace
GitHub: DeepFaceLab https://github.com/iperov/DeepFaceLab
GitHub: Neural Photo Editor https://github.com/ajbrock/Neural-Photo-Editor
GitHub: Stylegan2encoder https://github.com/robertluxemburg/stylegan2encoder
GitHub: Official code for StyleGAN2 https://github.com/NVlabs/stylegan2
- Introduction to Neural Networks or Advanced Neural Networks courses.
- Python or C++ ( > 1 year).
Rhythmus | Tag | Uhrzeit | Format / Ort | Zeitraum |
---|
Modul | Veranstaltung | Leistungen | |
---|---|---|---|
39-M-Inf-GP Grundlagenprojekt Intelligente Systeme | Gruppenprojekt | unbenotete Prüfungsleistung
|
Studieninformation |
Die verbindlichen Modulbeschreibungen enthalten weitere Informationen, auch zu den "Leistungen" und ihren Anforderungen. Sind mehrere "Leistungsformen" möglich, entscheiden die jeweiligen Lehrenden darüber.