Generative Modeling: Then, Now and Tomorrow?

This lecture by the instructor covers the evolution of generative modeling, from traditional approaches to the latest advancements. It delves into topics such as gradient-domain metropolis light transport, deep convolutional reconstruction, GANs as a two-player game, and the challenges faced in training generative adversarial networks. The presentation also explores the concept of progressive growing of GANs for improved quality, stability, and variation in generated images, along with the importance of dataset distillation and the dissection of GANs. The lecture concludes with a vision for the future of generative models, emphasizing the potential for high-quality outputs with less data, improved generalization, and enhanced interpretability.