Towards generating Deep Art
Event details
| Date | 24.08.2021 |
| Hour | 10:30 › 12:30 |
| Speaker | Ehsan Pajouheshgar |
| Category | Conferences - Seminars |
EDIC candidacy exam
exam president: Prof. Wenzel Jakob
thesis advisor: Prof. Sabine Süsstrunk
co-examiner: Prof. Pascal Fua
Abstract
We investigate recent deep generative models like StyleGAN2 and how they can be controlled by a textual description using the OpenAI Clip network.
Background papers
1 - A Style-Based Generator Architecture for Generative Adversarial Networks 1' - Analyzing and Improving the Image Quality of StyleGAN
2 - GAN DISSECTION: VISUALIZING AND UNDERSTANDING GENERATIVE ADVERSARIAL NETWORKS
3 - Editing in Style: Uncovering the Local Semantics of GANs
exam president: Prof. Wenzel Jakob
thesis advisor: Prof. Sabine Süsstrunk
co-examiner: Prof. Pascal Fua
Abstract
We investigate recent deep generative models like StyleGAN2 and how they can be controlled by a textual description using the OpenAI Clip network.
Background papers
1 - A Style-Based Generator Architecture for Generative Adversarial Networks 1' - Analyzing and Improving the Image Quality of StyleGAN
2 - GAN DISSECTION: VISUALIZING AND UNDERSTANDING GENERATIVE ADVERSARIAL NETWORKS
3 - Editing in Style: Uncovering the Local Semantics of GANs
Practical information
- General public
- Free
Contact
- edic@epfl.ch