Constrained Generative Adversarial Networks for Interactive Image Generation

04/03/2019
by   Eric Heim, et al.
0

Generative Adversarial Networks (GANs) have received a great deal of attention due in part to recent success in generating original, high-quality samples from visual domains. However, most current methods only allow for users to guide this image generation process through limited interactions. In this work we develop a novel GAN framework that allows humans to be "in-the-loop" of the image generation process. Our technique iteratively accepts relative constraints of the form "Generate an image more like image A than image B". After each constraint is given, the user is presented with new outputs from the GAN, informing the next round of feedback. This feedback is used to constrain the output of the GAN with respect to an underlying semantic space that can be designed to model a variety of different notions of similarity (e.g. classes, attributes, object relationships, color, etc.). In our experiments, we show that our GAN framework is able to generate images that are of comparable quality to equivalent unsupervised GANs while satisfying a large number of the constraints provided by users, effectively changing a GAN into one that allows users interactive control over image generation without sacrificing image quality.

READ FULL TEXT

page 1

page 4

page 5

page 6

page 12

research
08/10/2021

Interpreting Generative Adversarial Networks for Interactive Image Generation

Great progress has been made by the advances in Generative Adversarial N...
research
12/05/2017

Manifold-valued Image Generation with Wasserstein Adversarial Networks

Unsupervised image generation has recently received an increasing amount...
research
09/25/2019

Conditional Transferring Features: Scaling GANs to Thousands of Classes with 30

Generative adversarial network (GAN) has greatly improved the quality of...
research
11/16/2017

Two Birds with One Stone: Iteratively Learn Facial Attributes with GANs

Generating high fidelity identity-preserving faces has a wide range of a...
research
01/24/2018

Deep Interactive Evolution

This paper describes an approach that combines generative adversarial ne...
research
11/23/2020

HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms

While generative adversarial networks (GANs) can successfully produce hi...
research
05/14/2019

Kernel Mean Matching for Content Addressability of GANs

We propose a novel procedure which adds "content-addressability" to any ...

Please sign up or login with your details

Forgot password? Click here to reset