Uncanny Valley is a slightly silly look at facial recognition technologies, social media and augmented reality. I scraped tens of thousands of snapchat selfies, then had my GAN create its own. I was expecting to see more of the snapchat augmentations but it most often removed them and I was left with a fascinating array of selfies which I then put back into snapchat so that anyone could overlay them on top of their own faces. It’s about how we present different versions of ourselves on social media, wear different masks, but its also a great opportunity to have a giggle and share some silly and creepy selfies.
I have been lowkey obsessed with snapchat for a while now and decided to scrape some images from instagram to see what a neural network made of them. I expected the Generative Adversarial Network to meld together the Augmented Reality components with the faces to create something nightmarish. What I didn’t expect was the GAN to detect the commonality in the images and erase the components all together!
Working first with a DCGAN I trained until it reached mode collapse. I really enjoy watching neural networks collapse and the converging grids made for some really interesting works. While training I also used the face picker in snapchat to see if it would recognize any of the faces and was shocked when it separated them all out and used them all, with horrifying and hilarious results! I documented this progress on Twitter in a lengthy thread as I explored everything snapchat.
From there I used style transfer on some images to upsample them. For others I used resizing GANs and upsampling algorithms to bring the works up to print size from 128px. All of this ensures large enough prints for the art that will be on display. When the exhibition goes live I will publish the art and snapcodes on my website so that everyone can join in the fun even remotely!
If you have fun with this project please share it around and if you use the lenses tag me in or use #snapchatgan so I can see your wonderful works!