fashion_style_generation

Fashion Style Generator

Shuhui Jiang¹ and Yun Fu^1,2

¹Department of Electrical and Computer Engineering, Northeastern University, Boston, MA 02115, USA

²College of Computer and Information Science, Northeastern University, Boston, MA 02115, USA

{shjiang,yunfu}@ece.neu.edu

abstract

In this paper, we focus on a new problem: applying artificial intelligence to automatically generate fashion style images. Given a basic clothing image and a fashion style image (e.g., leopard print), we generate a clothing image with the certain style in real time with a neural fashion style generator. Fashion style generation is related to recent artistic style transfer works, but has its own challenges. The synthetic image should preserve the similar design as the basic clothing, and meanwhile blend the new style pattern on the clothing. Neither existing global nor patch based neural style transfer methods could well solve these challenges. In this paper, we propose an end-to-end feed-forward neural network which consists of a fashion style generator and a discriminator. The global and patch based style and content losses calculated by the discriminator alternatively back-propagate the generator network and optimize it. The global optimization stage preserves the clothing form and design and the local optimization stage preserves the detailed style pattern. Extensive experiments show that our method outperforms the state-of-the-arts.

What is fashion style generation?

In this paper, we focus on a novel problem: fashion style generation. It is different from existing online clothing design tools such as "Custom Ink" and "Ooshirts", which directly put a picked icon on the basic clothing. As shown in Figure 1, it puts the bear icon on a white T-shirt.

Figure 1: Example of existing online fashion design tool "Custom Ink".

In fashion style generation, as shown in Figure 2, with inputs of a basic clothing image and a style image, we automatically generate a clothing image blending with the new style while preserving the basic design. The definition of ``style'' in this paper is similar as the recent neural style transfer works [1]. Taking Van Gogh's ``Starry Night'' as the example style image, “style” is between the low-level color/texture (e.g., blue and yellow color, rough or smoother texture) and the high-level objects (e.g., house and mountain). ``Style'' is a relatively abstract concept. Fashion style generation has at least two practical usages. Designers could quickly see how the clothing looks like in a given style to facilitate the design processing. Shoppers could synthesize the clothing image with the ideal style and apply clothing retrieval tools to search the similar items.

Input Clothing Image Input Style Image Output Clothing

Figure 2. Our fashion style generation.

Framework

Reference

[1] Gatys, Leon A., Alexander S. Ecker, and Matthias Bethge. "A neural algorithm of artistic style." arXiv preprint arXiv:1508.06576 (2015).