Invertible Conditional GANs for image editing
arXiv:1611.06355
Abstract
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.
Accepted paper at NIPS 2016 Workshop on Adversarial Training
Cited by in corpus (6)
- Fader Networks: Manipulating Images by Sliding Attributes
- Triangle Generative Adversarial Networks
- Generative OpenMax for Multi-Class Open Set Classification
- GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data
- Unsupervised Multi-Domain Image Translation with Domain-Specific Encoders/Decoders
- Generative Adversarial Networks for Multimodal Representation Learning in Video Hyperlinking