TechRxiv
VitGAN.pdf (811.05 kB)
Download file

Vit-GAN: Image-to-image Translation with Vision Transformes and Conditional GANS

Download (811.05 kB)
preprint
posted on 20.10.2021, 13:08 by Yigit GunducYigit Gunduc
In this paper, we have developed a general-purpose architecture, Vit-Gan, capable of performing most of the image-to-image translation tasks from semantic image segmentation to single image depth perception. This paper is a follow-up paper, an extension of generator based model [1] in which the obtained results were very promising. This opened the possibility of further improvements with adversarial architecture. We used a unique vision transformers-based generator architecture and Conditional GANs(cGANs) with a Markovian Discriminator (PatchGAN) (https://github.com/YigitGunduc/vit-gan). In the present work, we use images as conditioning arguments. It is observed that the obtained results are more realistic than the commonly used architectures.

History

Email Address of Submitting Author

ygunduc@gmail.com

ORCID of Submitting Author

https://orcid.org/0000-0001-5210-4088

Submitting Author's Institution

Ankara University Development Foundation Private High School

Submitting Author's Country

Turkey

Usage metrics

Licence

Exports