Optimizing supervised generative adversarial networks via latent space regularizations

An apparatus for training a generator G of a Generative Adversarial Network (GAN), comprising:

• a memory;
• and
• a processor, the processor is configured to execute instructions stored in the memory to:
• input, to an encoder E, a target data Y;
• input, to the encoder E, an output G(Z) of the generator G,
• wherein the generator G generates the output G(Z) in response to receiving a random sample Z, and
• wherein a discriminator D of the GAN is trained to distinguish between the output G(Z) and the target data Y;
• train the encoder E to minimize a difference between a first latent space representation E(G(Z)) of the output G(Z) and a second latent space representation E(Y) of the target data Y, wherein the output G(Z) and the target data Y are input to the encoder E;
• and
• use the first latent space representation E(G(Z)) and the second latent space representation E(Y) to constrain the training of the generator G.

An apparatus for generating a super resolution image, comprising:

• a memory;
• and
• a processor, the processor is configured to execute instructions stored in the memory to:
• receive, by a generator G, an input corresponding to a low resolution image;
• and
• output, from the generator G, a super resolution image corresponding to the low resolution image, wherein the generator G is trained using a Generative Adversarial Network (GAN), the GAN comprising:
• the generator G;
• an encoder E;
• and
• a discriminator D, wherein outputs of the encoder E are used to constrain the training of the generator G, wherein the outputs of the encoder comprise:
• a first latent space representation E(G(Z)) of an output G(Z) of the generator G, wherein Z corresponds to a training low-resolution image and G(Z) corresponds to a generated high-resolution image;
• and
• a second latent space representation E(Y) of a training high-resolution image Y.