Amazon – predictive personalised 3D body models
Snap est aussi très actif sur le sujet, l'enjeux sera la précision du modèle et si ça peut servir pour de l'habillement.
Amazon is working on generating 3D body models of people based on 2D images of them.
Currently, 3D modelling of human bodies require large and expensive scanners, making them impractical to do in your own home.
Amazon is looking to create an app where users will be instructed to take photos of a user from different directions. Based on these images, Amazon will determine a 3D model of a user, based on estimated body measurements. For example, Amazon will estimate a user’s weight, body fat, body dimensions (e.g. arm length), and skin texture / colour.
With this model, users could then begin to interact with the model. For example, a user may wonder what they could look like if they lost some body fat and increased their muscle. Amazon’s interface will provide users with a sliding interface to adjust these parameters.
What’s Amazon’s game plan?
Well, in #017 PATENT DROP, we saw that Amazon filed a patent application for users to be able to order customised clothing. In that filing, there was a small mention of Amazon looking to capture a user’s measurements via submitted photos or through a camera.
This latest filing seems to be how Amazon will look to enable users to maybe order customised clothing that is right for their body measurements.
But before that, Amazon having 3D body models of users could allow users to virtually try out on items of clothing to make sure that they’re ordering the right size. In theory, this could help minimise returns, and in turn save on costs. This could also become a separate technology layer that Amazon sells to other e-commerce platforms.
And maybe more wildly, could there be interesting media applications from creating a database of 3D human body scans? For example, imagine if you could ‘inject’ yourself into an Amazon Prime movie as one of the main actors.
Will keep an eye out for any future developments around this.
via Patent Drop : lire l’article source