AI fashion designer can create outfits based on your choice!

Scientists have debeloped an artificial intelligence 'fashion designer' that can create custom apparel designs based on a person's preferences.
The system, developed by researchers at the University of California San Diego in the US, aimed to test how well tools from artificial intelligence (AI) and machine learning can help the fashion industry and consumers.
While there are many algorithms and tools to help online retailers recommend designs to potential buyers, team wanted to see if it would be possible to crunch preference and other data to make recommendations, and enable computers to produce custom clothing designs.
"We show that our model can be used generatively, ie given a user and a product category, we can generate new images (in this case clothing items) that are most consistent with the user's personal taste," said Wang-Cheng Kang, PhD student at UC San Diego.

"This represents a first step toward building systems that go beyond recommending existing items from a product corpus, to suggesting styles and helping to design new products," said Kang.
Researchers focused on devising a system to create better recommendations, particularly in the case of 'visual' recommendations, where consumers can be swayed by how the product looks, as in the case of fashion apparel or artworks.

"This suggests a new type of recommendation approach that can be used for recommendation, production and design," said Julian McAuley, professor at UC San Diego.
"These frameworks can lead to richer forms of recommendation, where content recommendation and content generation are more closely linked," said McAuley.

"Building effective recommender systems for domains like fashion is challenging due to the high level of subjectivity and the semantic complexity of the features involved," he said.
The team demonstrated that recommendation performance can be significantly improved by learning 'fashion aware' image representations directly, by training the image representation and the recommender system jointly.