papers AI Learner
The Github is limit! Click to go to the new site.

Disentangling Multiple Conditional Inputs in GANs

2018-06-20
Gökhan Yildirim, Calvin Seward, Urs Bergmann

Abstract

In this paper, we propose a method that disentangles the effects of multiple input conditions in Generative Adversarial Networks (GANs). In particular, we demonstrate our method in controlling color, texture, and shape of a generated garment image for computer-aided fashion design. To disentangle the effect of input attributes, we customize conditional GANs with consistency loss functions. In our experiments, we tune one input at a time and show that we can guide our network to generate novel and realistic images of clothing articles. In addition, we present a fashion design process that estimates the input attributes of an existing garment and modifies them using our generator.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1806.07819

PDF

https://arxiv.org/pdf/1806.07819


Similar Posts

Comments