A team of researchers from Adobe Research and the University of California, San Diego, have displayed how neural network and artificial intelligence (AI) one day could create customized designs for apparel to assist apparel manufacturers and vendors in meet consumers’ demand and provide them with exactly what they want. Wang-Cheng Kang, the first-author and a Ph.D. (computer science) student at the University of California, stated that they have proved that their model can be utilized generatively, that is, they can create new clothing items that are according to the consumer’s interests and choices. “This symbolizes the first step toward creating systems that move past just recommending the existing items from the product portfolio to offering new styles and designs,” he added.
The findings of this research had been published on ArXiv in early November 2017. Along with Wang-Cheng Kang, Julian McAuley, the professor of Computer Science and Engineering at the University of California, created a team with industry experts Zhaowen Wang and Chen Fang and from Adobe Research. “This suggests a novel type of approach that can be utilized for recommendation, design, and production,” wrote McAuley and his teammates. “These frameworks are able to lead to a richer form of recommendation, in which content generation as well as recommendation are more closely connected,” they added. The project is aimed at testing how well machines from AI and machine learning can assist consumers and the fashion industry.