TY  - CONF
AU  - Guim Perarnau
AU  - Joost Van de Weijer
AU  - Bogdan Raducanu
AU  - Jose Manuel Alvarez
A2  - NIPSW
PY  - 2016//
TI  - Invertible conditional gans for image editing
BT  - 30th Annual Conference on Neural Information Processing Systems Worshops
N2  - Generative Adversarial Networks (GANs) have recently demonstrated to successfully approximate complex data distributions. A relevant extension of this model is conditional GANs (cGANs), where the introduction of external information allows to determine specific representations of the generated images. In this work, we evaluate encoders to inverse the mapping of a cGAN, i.e., mapping a real image into a latent space and a conditional representation. This allows, for example, to reconstruct and modify real images of faces conditioning on arbitrary attributes.Additionally, we evaluate the design of cGANs. The combination of an encoderwith a cGAN, which we call Invertible cGAN (IcGAN), enables to re-generate realimages with deterministic complex modifications.
L1  - http://refbase.cvc.uab.es/files/PWR2016.pdf
N1  - LAMP; ADAS; 600.068
ID  - Guim Perarnau2016
ER  -