Getting dressed with Augmented Reality, AI
Cher Horowitz’s secret from the film “Clueless” had an innovative computer system that helped her put together outfits. Back in 1995, the concept teased what it might be like to get dressed in the future.
Technology has evolved a lot since then, but closets have been in the main undamaged by innovation.
Now, that’s starting to change.
“If algorithms do their job well, people will spend less time thinking about what to wear,” said Ranjitha Kumar, an assistant professor in the Department of Computer Science at the University of Illinois at Urbana-Champaign.
Starting from artificial intelligence and gadgets to smart fabrics and virtual reality, technology is hovering to breathe innovation into not only how we dress but how we shop.
The most familiar example is Amazon’s Echo Look, which received significant buzz when it was announced earlier this year. The gadget ($200) serves as a style assistant that help you to decide what to wear. Like Amazon’s smart speakers, the Echo Look will tell you the weather or play music automatically. But the oval-shaped product also has a voice-controlled camera for taking photos for you in diverse outfits. It works beside an app.
After taking photos of you in two outfits in front of the device, its built-in Style Check tool decide which one is the perfect. It leans on a grouping of machine learning technology and human insight.
Amazon’s “fashion specialists” train the software to be an evaluator of style. The automated results consider “outfit, color, styling, seasons and modern trends.” It’ll also suggest related styles to buy from various brands. Through test, we found that the suggestions can be hit or miss.
“The brand selection is restricted, and while the Amazon Echo Look may help you decide between two looks, it can’t take into account the total perspective of where you’re going,” said personal stylist and creative director Taylor Okata.
Okata, whose clients include E! And SELF Magazine doesn’t think about the technology a threat to his work: “There’s just that interpersonal announcement that it just doesn’t have.”
Meanwhile, the retail experts say, the Echo Look’s success will depend on if it adds more value than just asking a friend for fashion advice.
Sucharita Mulpuru, an analyst at research firm Forrester, said those buying the device are early on adopters — and it lacks extensive appeal.
Other companies are taking up augmented and virtual reality to help people choose what to wear. For example, Startup Obsess developed an augmented and virtual reality shopping platforms, so customers can shop without having to go to a store.
In July, the company united with Vera Bradley to roll out VR experiences at 10 of its stores. While wearing a Google Daydream VR, shoppers can shift a bed around in VR, and see Vera Bradley comforters, quilts and pillows up close in a virtual store.
Apple’s new augmented reality platform builds on a related concept, allowing developers to create augmented reality apps. For example, the new IKEA Place app lets users preview furniture virtually from their home. The tool has more extensive appeal because it doesn’t require a headset.
Fabrics are getting smarter, too. Earlier this year, JanSport unveiled a model for a high-tech backpack with programmable fabric. The backpack lets users share a song, music video, Facebook page or website link with anyone close to by holding up their Smartphone and using a corresponding app. The backpack could give teens a new way to express themselves.
The concept comes from MIT professor Yoel Fink, the CEO of Advanced Functional Fabrics of America, a nonprofits that aims to reinvent fabrics as programmable devices.
“Fabrics are among the earliest forms of human expression and they’ve been around for thousands of years,” Fink said. “But they really haven’t changed much from a functional perspective. Our goal is to change what fabrics [do].”
The team’s latest prototype is a sports jersey that would let viewers at a game scan an app over players to see their stats, such as assists, rebounds, and points. The group will soon test the New jerseys with the MIT basketball team.
Artificial intelligence could also have a huge impact on style, especially as a tool to help retailers predict trends and keep fashion houses in front of the curve. Researchers are already working on such type of solutions using AI and machine learning.
For example, Kumar from the University of Illinois and her team are working at algorithmically identifying fashion “influencers” and emerging trends.
Machine learning techniques that analyze the content of tweets, the group has identified more than 27,000 fashion associated accounts on Twitter as the top trendsetters.
“We’re now tracking these influencers and the content they post to model micro-trends and predict their lifetime,” she said.
However, the challenge is the speed at which fashion trends revolutionize. They can go in weeks or sometimes even a few days, according to Kumar.
Kavita Bala, a professor in the Computer Science Department at Cornell University, is also analyzing social media platforms to come across for fashion trends. For example, her team can plot how often people are wearing a definite clothing item over time for a particular city in the world.
But Bala said style reference presents another challenge: “People have very distinctive, subtle and maverick style and they’re very picky about it.”
While some AI approaches are already in the works, other tech, like shopping with a VR headset in your home, is still years away. It’s also unclear how quickly consumers would adopt this.
“All of that is becoming possible, but we’re not quite there yet,” said Obsess’ Singh.