Pix2pixHD was proposed by Ting-Chun Wang, Ming-Yu Liu, and Jun-Yan Zhu, et. al. in their paper, High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs, which was an upgraded version of the pix2pix model. The biggest improvement of pix2pixHD over pix2pix is that it supports image-to-image translation at 2,048x1,024 resolution and with high quality.
Pix2pixHD – high-resolution image translation
Model architecture
To make this happen, they designed a two-stage approach to gradually train and refine the networks, as shown in the following diagram. First, a lower resolution image of 1,024x512 is generated by a generator network, 
, called the global generator (the red box). Second, the image is enlarged...
