pix2pix

The pix2pix network was introduced by Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A. Efros in their paper titled Image-to-Image Translation with Conditional Adversarial Networks, which is available at the following link: https://arxiv.org/abs/1611.07004. The pix2pix network has similar use cases to the CycleGAN network. It can convert building labels to pictures of buildings (we will see a similar example in the pix2pix chapter), black and white images to color images, images taken in the day to night images, sketches to photos, and aerial images to map-like images.