https://openreview.net/forum?id=QMGQ2uA50R&referrer=%5Bthe%20profile%20of%20Samuel%20Mermet%5D(%2Fprofile%3Fid%3D~Samuel_Mermet1)
StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation | OpenReview
Most image-to-image translation models postulate that a unique correspondence exists between the semantic classes of the source and target domains. However...
image toleveragingsteganographynontranslation