Computational creativity and the future of AI

Fitle gives users a 3D avatar of themselves for virtually trying on clothes


July 29, 2014

Fitle wants to provide users with a 3D avatar of themselves with which to try on clothes w...

Fitle wants to provide users with a 3D avatar of themselves with which to try on clothes when shopping online

Image Gallery (4 images)

A new service is promising to end the uncertainty of how clothes will look or fit when shopping on the web. Fitle aims to provide users with a 3D avatar of themselves with which to "try on" clothes online. The company says it will eventually offer the world's largest clothes database via partners.

A number of technologies have already been created aimed at helping people to judge the look at fit of clothes when shopping online. is a solution developed for online retailers that allows people to input their measurements and dress a virtual mannequin to gauge clothing fit. Verisize, meanwhile, provides users with size equivalents across clothing brands.

While these tools can be useful, Fitle says that it can create a 3D avatar of an individual that not only looks like them, but that is morphologically exact. Indeed, it claims to provide a 99 percent accurate representation of the user.

User need only provide their height and four photos to create their 3D avatar

Fitle avatars are created using the height measurement of a user and four photos of them. An algorithm is used to extract more than 50 parameters based on how a user looks, while another is used to create a 3D reconstruction of the user. Fitle says the end results are photo-realistic.

The company also uses its recognition and reconstruction algorithms to digitize clothing from its partners. By doing so, Fitle says it is able to generate "accurate 3D versions of clothes based on their dimensions, size and material," and that users can therefore be confident that the look and fit of the clothes on their avatars will be true to life.

An algorithm is used to extract more than 50 parameters based on how a user looks

Amongst the other benefits that Fitle says its technology will provide is the ability to show users only clothes that will fit them and that match their style, based on previous purchases. Users can scan the barcode of existing clothes to see what they would look like when paired with online items, if the existing item has already been digitized. Clothes can also be saved to a virtual wardrobe in order to try out different outfits or to see how certain items will match with potential purchases in the future.

Fitle says that it has the catalogs of over 250 partner brands already digitized. Partner catalogs are kept up-to-date with new items, changes in price and product availability.

Users can scan the barcodes of existing clothes to see how they would look with potential ...

The company is currently running a Kickstarter campaign to raise funds for the industrialization of its 3D clothes modeling process, to increase its partner network, to further improve its accuracy and to run beta testing of the technology. Individuals can pledge to receive, amongst other things, a smartphone case, a watch or beta access to the site. The campaign looks set to miss its target, but Fitle says it will launch regardless. It is due to go live first in the US and France by February 2015.

Fitle's Kickstarter pitch video can be seen below.

Sources: Fitle, Kickstarter

About the Author
Stu Robarts Stu is a tech writer based in Liverpool, UK. He has previously worked on global digital estate management at Amaze and headed up digital strategy for FACT (Foundation for Art and Creative Technology). He likes cups of tea, bacon sandwiches and RSS feeds.   All articles by Stu Robarts

Great idea, but the reason it hasn't been done before is that it is really, really hard to do right. Not quite moonshot difficulty, but not far from it. I wish them luck - if they can make it work they will make billions.

30th July, 2014 @ 09:35 am PDT

Does the landscape mode make me look fat? Click...portrait better.

Bob Flint
31st July, 2014 @ 09:32 am PDT
Post a Comment

Login with your gizmag account:

Or Login with Facebook:

Related Articles
Looking for something? Search our 31,282 articles
Recent popular articles in Good Thinking
Product Comparisons