StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation

arXiv:2403.20142v1 Announce Type: new
Abstract: Most image-to-image translation models postulate that a unique correspondence exists between the semantic classes of the source and target domains. However, this assumption does not always hold in real-world scenarios due to divergent distributions, different class sets, and asymmetrical information representation. As conventional GANs attempt to generate images that match the distribution of the target domain, they may hallucinate spurious instances of classes absent from the source domain, thereby diminishing the usefulness and reliability of …

arxiv cs.cv eess.iv image image-to-image image-to-image translation steganography translation type