# Constrained Generative Adversarial Networks for Interactive Image Generation

## TL;DR

This paper introduces a novel GAN framework enabling interactive image generation through user-provided relative constraints, allowing for controlled, high-quality image synthesis aligned with user preferences.

## Contribution

The work develops a GAN model that incorporates iterative user feedback via relative constraints, enhancing interactive control without compromising image quality.

## Key findings

- Generates images of comparable quality to traditional GANs.
- Successfully incorporates multiple user constraints in image generation.
- Enables flexible semantic control over generated images.

## Abstract

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.