With this feature, users can take a selfie within the app, and it will automatically create the sticker pack. In a blog post, Jennifer Daniel, expressions creative director for Google Allo, said the feature uses a combination of neural networks and the work of artists to create the packs.
Once a sticker pack has been created, users can customize their illustrated appearance with different facial expressions, props and more before sharing the stickers in in-app conversations. Daniel said there are more than 563 quadrillion possible feature combinations available.
In the study of aesthetics, a well-known problem is the uncanny valley—the hypothesis that human replicas that appear almost, but not exactly, like real human beings can feel repulsive. In machine learning, this could be compounded if (you) were confronted by a computer’s perception of you versus how you may think of yourself, which can be at odds.
Rather than aiming to replicate a person’s appearance exactly, pursuing a lower-resolution model, like emojis and stickers, allows the team to explore expressive representation by returning an image that is less about reproducing reality and more about breaking the rules of representation.