High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

This course teaches high-resolution image synthesis and semantic manipulation using Conditional Generative Adversarial Networks (GANs). The learning outcomes include understanding how to improve photorealism and resolution through techniques such as Coarse to Fine Generation and Multi-Scale Discriminators. Students will also learn to use Instance Maps and learn an Instance Level Feature Embedding. The teaching method involves a combination of theoretical lectures and practical demonstrations. This course is intended for individuals interested in advanced image processing, computer vision, and machine learning.