Online retailer Zalando has teamed up with Google to create a new virtual fashion experience letting shoppers create their own designs in 3D. The initiative called Project Muze uses a neural network trained with design preferences such as colours, textures and imagery. By answering a few questions such as mood and style the shopper will generate a design based on the answers as well as data from the Google Fashion Trends Report and top trending objects from Zalando’s online platform.
The project taps in to the trend of using machine learning to create a personalized experience using Google’s open-source platform TensorFlow combined with a set of aesthetic parameters. It launched at trend show Bread&butter in Berlin earlier this fall where a few handpicked designs were highlighted. The chosen pieces were later to be translated into real garments. Considering the visual experience the project clearly shows a big gap between digital and physical dimensions yet to be filled. However the concept of combining algorithms with 3D product interaction suggests a potential future where shoppers can virtually create their own products based on personal data.
Read more about 3D avatars and CGI in fashion
Customizable characters or the ability to create your very own avatar is a well known element in video games. Major game studios are even creating customization interfaces that are reminiscent of a real world fitting room including the ability to pick characteristics such as eye colour, skin tone and hair style.
The importance of identification has positioned character customization as a component for game studios with graphic ambitions. It has also raised the issue of lack of diversity in an industry with reputation to only be representing white men as has historically been the only character option to choose from. Insomniac games is one of the studios rebelling against that norm in their action game Sunset Overdrive. In it, the players are given the option of playable female character as well as customization options that are unrelated to gender. It points out the importance of identification in recreating yourself digitally: you not only have the possibility to represent your physical world self, but who you want to be or, even let your imagination take you to a new digital self.
In Bungie’s Destiny as well as BioWare’s fantasy title Dragon age: Inquisition, the player can choose his or her appearance with high level of detail in everything from race, gender and class to face features. As computer graphics have advanced into close in on photorealism, the gaps in implementation have decreased. The type of self-visualizing which has so far only been used for character design is now of interest when we digitize our lives for different kinds of services.
Fashion ecommerce is constantly looking for new visualization tools to provide stunning digital experiences with technology used by game artists. 3D content such as creating personal avatars, virtually trying on 3D rendered garments or customizing products are services now popping up globally to bring us new ways of living our digital lives. The skillset of a CG artist is suddenly pure gold in a new fashion landscape. As shown by the advances of self-visualisation in gaming we will most likely see great innovations in the near future at this very intersection, taking the shown examples out of their original context. When it comes to visual experiences fashion has everything to learn from game art and digital storytelling.
Also read about the work of Joseph Cross and Chris Wells