GAN Papers to Read in 2020

Generative Adversarial Networks (GANs) are one of the most innovative ideas proposed in this decade. At its core, GANs are an unsupervised model for generating new elements from a set of similar elements. For instance, to produce original face pictures given a collection of face images or create new tunes out of preexisting melodies. GANs have found applications for image, text, and sound generation, being at the core of technologies such as AI music, deep fakes, and content-aware image editing. Besides pure generation, GANs have also been applied to transforming images from one domain to another and as a means for style transfer.