Adversarial training alone can mimic an autoencoder under strong capacity assumptions, which the paper proposes as the mechanism behind GAN-only image-to-image translation.
Multimodal unsuper- vised image-to-image translation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Mechanisms of Generative Image-to-Image Translation Networks
Adversarial training alone can mimic an autoencoder under strong capacity assumptions, which the paper proposes as the mechanism behind GAN-only image-to-image translation.