H-GAN: the power of GANs in your Hands

03/27/2021 ∙ by Sergiu Oprea, et al. ∙ 22

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 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 successfully apply the generated images to the hand classification task.



There are no comments yet.


page 1

page 3

page 4

page 5

page 7

Code Repositories


Reference code for the paper "HandGAN - The power of GANs in yout Hands" (IJCNN 2021)

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.