FashionGAN: Display your fashion design using Conditional Generative Adversarial Nets

Abstract

Virtual garment display plays an important role in fashion design for it can directly show the design effect of the garment without having to make a sample garment like traditional clothing industry. In this paper, we propose an end‐to‐end virtual garment display method based on Conditional Generative Adversarial Networks. Different from existing 3D virtual garment methods which need complex interactions and domain‐specific user knowledge, our method only need users to input a desired fashion sketch and a specified fabric image then the image of the virtual garment whose shape and texture are consistent with the input fashion sketch and fabric image can be shown out quickly and automatically. Moreover, it can also be extended to contour images and garment images, which further improves the reuse rate of fashion design. Compared with the existing image‐to‐image methods, the quality of images generated by our method is better in terms of color and shape.

Generative Adversarial Networks–Enabled Human–Artificial Intelligence Collaborative Applications for Creative and Design Industries: A Systematic Review of Current Approaches and Trends

“… Cui et al (2018) presented a tool for designers to visualize more complete fashion designs quickly. Users provide both an input sketch and a material.…”

“…Right: When designing, it can be cumbersome to iterate overall the possible material options. Cui et al (2018) presented a system that attempts to optimize the process.…”

“…The authors performed some user studies to determine the degree to which their system produced preferred designs over state-of-the-art approaches and found a very significant improvement in likability scores for the garments produced by their system. Cui et al (2018) presented a tool for designers to visualize more complete fashion designs quickly. Users provide both an input sketch and a material.…”

Prediction of face age progression with generative adversarial networks

“…After that, it took this information to code and compare the images of each face. Then, deep learning had gained tremendous attention in the computer vision field that had produced a remarkable result in many fields [ 3 , 9 , 15 , 31 , 33 ]. Now, the research on GAN is exploring the main aspect that is, an improvement in the training process and the second is positioning the GANs in real-world applications [ 17 , 60 ].…”

Artificial intelligence in the fashion industry: consumer responses to generative adversarial network (GAN) technology

“…Several researchers have developed GANs to design fashion products: shoeGAN utilises GoogleNet-based, fully connected neural network classifiers to extract vector values of images which become inputs for shoe designs (Deverall et al , 2017); FashionGAN enables specific fabric colours and patterns to be applied to a single sketch as an input value, thereby overcoming the complexities involved in creating 3D virtual clothing (Cui et al , 2018) and attribute manipulation GAN solves problems involving many attributes by introducing class activation maps to the generator (Ak et al , 2019). Other researchers have developed GANs that transform clothing designs based on images of a fashion model, including: a GAN that outputs altered images based on text entered by a designer (Zhu et al , 2017a); an end to end Swapnet to create a 3D image by superimposing posture, form and clothes from different images and adding warping and texturing modules to the vanillaGAN (Raj et al , 2018) and a category-supervised GAN that classifies clothing in images using YOLO and then uses CatGAN to produce a tiled image (Zhang et al , 2018).…”