We have two generators, and . The role of is to learn the mapping from to . As mentioned above, the role of is to learn to translate photos to paintings, as shown in the following figure:
It tries to generate a fake target image, which implies it takes a source image, , as input and generates a fake target image, :
The role of the generator, , is to learn the mapping from to and learn to translate from the painting to a real picture, as shown in following figure:
It tries to generate a fake source image, which implies it takes a target image, , as input and generates a fake source image, :