A university research group creates an avatar to help online shoppers feel how clothes fit them

What if you could “feel” the way clothes fit before buying them online?

As the COVID-19 pandemic continues to fuel demand for online shopping, a research team from The University of Saskatchewan is developing a way to solve the growing problem of clothing returns with an avatar that “senses” how clothing fits digitally.

Computer science professor Raymond Spiteri and his team have developed personalized avatars that can try on clothes while people shop online and detect how the clothes will actually fit the shopper.

Here’s how it works:

Photo by David Stobbe

First, the user uploads a few photos of themselves in more fitted clothes. Data such as their height, weight, gender and body measurements are also required to create a personalized avatar, Spiteri said. This process makes it possible to analyze the appearance and the cut of the clothes according to the morphology of the buyer.

The next phase involves the actual garment.

“We also represent the garment as a mesh of particles. And we can use physics to kind of say how flexible and stretchy the garment is, and how it will then interact with your avatar,” he said.

Then a comfort map or heat map is displayed to show how the clothes actually fit. For example, if the shirt is too tight under the arms, the heat map will show up in red around that area. Based on this, buyers can determine whether to increase or decrease their size.

Additional Features

While most commercial avatars involve a Photoshop-like process, Spiteri and the research team create a more realistic experience that mimics trying on clothes in person.

The software is also able to identify the type of material in the garments. For now, the project is only for t-shirts as it is just a garment to work on, but there are plans to expand to other garments and shoes, according to Spiteri.

He also said the researchers also plan to build a social support network so shoppers can talk about the sizes of different garments.

“The idea could not only give them the confidence to buy, but also allow them to be happy with what they get and not have to come back. [anything].”

According to a 2019 CNBC item, 30-40% of online clothing and shoe purchases are returned. In the same article, David Sobie, co-founder and CEO of Happy Returns, said: “Shoppers return 5-10% of what they buy in-store, but 15-40% of what they buy online. “.

This shopping tool could solve some of the return issues that retailers have had over the past year and a half.

And after?

The next step for the University of Saskatchewan research group is to work with retailers to make the technology available to the general public. Spiteri said the group is still in the “convincing” stage, as the software is still in development.

“Retailers are obviously not going to come on board. We certainly still have some way to go to get customer feedback and adjust it and then integrate it into the various retailer websites.

A shopping avatar that offers an in-person dressing room experience could be a game-changer for the world of online shopping, and Spiteri and the project are credited for it.

This work is one of 16 research projects that have collectively earned Spiteri the Mitacs Award for Outstanding Leadership — Professorassigned by Mitacs. Mitacs is a national innovation organization that solves business challenges with research solutions from academic institutions.

The award will be presented in a hybrid ceremony on November 23 at the National Arts Center in Ottawa.

Elizabeth J. Harless