Invertible Conditional GANs for image editing

11/19/2016
by   Guim Perarnau, et al.
0

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 encoder with a cGAN, which we call Invertible cGAN (IcGAN), enables to re-generate real images with deterministic complex modifications.

READ FULL TEXT

page 7

page 8

research
05/31/2016

Adversarial Feature Learning

The ability of the Generative Adversarial Networks (GANs) framework to l...
research
09/11/2020

Inverse mapping of face GANs

Generative adversarial networks (GANs) synthesize realistic images from ...
research
06/09/2021

Stein Latent Optimization for GANs

Generative adversarial networks (GANs) with clustered latent spaces can ...
research
06/11/2020

Conditional Sampling With Monotone GANs

We present a new approach for sampling conditional measures that enables...
research
06/20/2018

Disentangling Multiple Conditional Inputs in GANs

In this paper, we propose a method that disentangles the effects of mult...
research
01/23/2020

Information Compensation for Deep Conditional Generative Networks

In recent years, unsupervised/weakly-supervised conditional generative a...
research
07/16/2017

Generative Adversarial Network based on Resnet for Conditional Image Restoration

The GANs promote an adversarive game to approximate complex and jointed ...

Please sign up or login with your details

Forgot password? Click here to reset