Inspirational Adversarial Image Generation

06/17/2019
by   Morgane Riviere, et al.
0

The task of image generation started to receive some attention from artists and designers to inspire them in new creations. However, exploiting the results of deep generative models such as Generative Adversarial Networks can be long and tedious given the lack of existing tools. In this work, we propose a simple strategy to inspire creators with new generations learned from a dataset of their choice, while providing some control on them. We design a simple optimization method to find the optimal latent parameters corresponding to the closest generation to any input inspirational image. Specifically, we allow the generation given an inspirational image of the user choice by performing several optimization steps to recover optimal parameters from the model's latent space. We tested several exploration methods starting with classic gradient descents to gradient-free optimizers. Many gradient-free optimizers just need comparisons (better/worse than another image), so that they can even be used without numerical criterion, without inspirational image, but with only with human preference. Thus, by iterating on one's preferences we could make robust Facial Composite or Fashion Generation algorithms. High resolution of the produced design generations are obtained using progressive growing of GANs. Our results on four datasets of faces, fashion images, and textures show that satisfactory images are effectively retrieved in most cases.

READ FULL TEXT
research
05/24/2019

Generative Latent Flow: A Framework for Non-adversarial Image Generation

Generative Adversarial Networks (GANs) have been shown to outperform non...
research
07/06/2022

Exploring Generative Adversarial Networks for Text-to-Image Generation with Evolution Strategies

In the context of generative models, text-to-image generation achieved i...
research
11/28/2022

Conditional Progressive Generative Adversarial Network for satellite image generation

Image generation and image completion are rapidly evolving fields, thank...
research
07/09/2021

Deep Image Synthesis from Intuitive User Input: A Review and Perspectives

In many applications of computer graphics, art and design, it is desirab...
research
06/21/2018

Fashion-Gen: The Generative Fashion Dataset and Challenge

We introduce a new dataset of 293,008 high definition (1360 x 1360 pixel...
research
12/07/2021

A Generic Approach for Enhancing GANs by Regularized Latent Optimization

With the rapidly growing model complexity and data volume, training deep...
research
08/08/2021

BIGRoC: Boosting Image Generation via a Robust Classifier

The interest of the machine learning community in image synthesis has gr...

Please sign up or login with your details

Forgot password? Click here to reset