Image Generation with Semantic Information
Masterarbeit
Im Rahmen des Projekts Semantic Scene Analysis

Description

With the development of neural networks, high-quality images can be generated automatically with different conditions.

In this project, when designing a generative model (e.g. Generative Adversarial Network), it is necessary to consider the objects' location/shape/texture and decode the relationships between them.

It is a challenging but potential work. Please send me an email with your resume if you have interest.

Key words: Generative adversarial network (GAN), Image generation/synthesis, semantic analysis.

Requirements

Good programming skill

Contact person: Yuren Cong