Oprea, Sergiu, Karvounas, Giorgos, Martínez González, Pablo, Kyriazis, Nikolaos, Orts-Escolano, Sergio, Oikonomidis, Iason, Garcia-Garcia, Alberto, Tsoli, Aggeliki, Garcia-Rodriguez, Jose, Argyros, Antonis
H-GAN: the power of GANs in your Hands
URI: http://hdl.handle.net/10045/114586
DOI: 
ISSN: 
Abstract: 
We present HandGAN (H-GAN), a cycle-consistent adversarial learning approach implementing multi-scale perceptual discriminators. It is designed to translate synthetic images of hands to the real domain. Synthetic hands provide complete ground-truth annotations, yet they are not representative of the target distribution of real-world data. We strive to provide the perfect blend of a realistic hand appearance with synthetic annotations. Relying on image-to-image translation, we improve the appearance of synthetic hands to approximate the statistical distribution underlying a collection of real images of hands. H-GAN tackles not only the cross-domain tone mapping but also structural differences in localized areas such as shading discontinuities. Results are evaluated on a qualitative and quantitative basis improving previous works. Furthermore, we relied on the hand classification task to claim our generated hands are statistically similar to the real domain of hand.
Keywords:Synthetic-to-real, Generative adversarial networks, Cycle-consistency, Perceptual discriminator
software