DeSIGN: Design Inspiration from Generative Networks

04/03/2018
by   Othman Sbai, et al.
0

Can an algorithm create original and compelling fashion designs to serve as an inspirational assistant? To help answer this question, we design and investigate different image generation models associated with different loss functions to boost creativity in fashion generation. The dimensions of our explorations include: (i) different Generative Adversarial Networks architectures that start from noise vectors to generate fashion items, (ii) a new loss function that encourages creativity, and (iii) a generation process following the key elements of fashion design (disentangling shape and texture makers). A key challenge of this study is the evaluation of generated designs and the retrieval of best ones, hence we put together an evaluation protocol associating automatic metrics and human experimental studies that we hope will help ease future research. We show that our proposed creativity loss yields better overall appreciation than the one employed in Creative Adversarial Networks. In the end, about 61 human designers rather than by a computer while also being considered original per our human subject experiments, and our proposed loss scores the highest compared to existing losses in both novelty and likability.

READ FULL TEXT

page 1

page 6

page 8

page 10

research
06/20/2018

Disentangling Multiple Conditional Inputs in GANs

In this paper, we propose a method that disentangles the effects of mult...
research
01/25/2021

GUIGAN: Learning to Generate GUI Designs Using Generative Adversarial Networks

Graphical User Interface (GUI) is ubiquitous in almost all modern deskto...
research
08/08/2017

Binary Generative Adversarial Networks for Image Retrieval

The most striking successes in image retrieval using deep hashing have m...
research
04/12/2017

MAGAN: Margin Adaptation for Generative Adversarial Networks

We propose the Margin Adaptation for Generative Adversarial Networks (MA...
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
09/08/2019

TorchGAN: A Flexible Framework for GAN Training and Evaluation

TorchGAN is a PyTorch based framework for writing succinct and comprehen...
research
01/21/2018

Decoupled Learning for Conditional Adversarial Networks

Incorporating encoding-decoding nets with adversarial nets has been wide...

Please sign up or login with your details

Forgot password? Click here to reset