Cats
Brief
"Slices of Shared Selves" is a duo of interactive web installtions that examines how our image and identity are perceived and understood in a society infiltrated by ubiquitous AI systems. Each piece in the duo is a mirror that presents a slice of our shared-selves in the eyes of an AI, reflected off an algorithmically aligned/mis-aligned collective of generative faces, plus the the viewer's face in real-time.
The two mirrors in this duo are based on different media - "A Slice of Shared Self" (2021) is based on 48 short video-clips, and "A Slice of Hundreds Shared Selves" (2022) is based on 484 generated art portraits. The viewers are asked to grant access to the camera, observe, move / turn / tilt / lean forward or backward to find different faces (if they want to), and hold their head position once in a while. Their feed won't be recorded.
The project aims to ask the following: Are we more connected or more divided? Are we becoming the greatest collective ever, or are we losing the notion of an individual?" Abstracted, generalized, and profiled, the way we're blended in these systems has already reshaped our perception of the world. When phones and webcams become our new mirror, when the reflected us is no longer the real us, how would we confront and live with these polarized/muted fractions of ourselves, and how would we move forward?
Concept & Building Process
This piece is inspired by R. Luke Dubois's Pop Icon: Bowie piece, and the recent advancement in high-resolution AI image synthesis. While AI is now capable of producing images that look exactly like photos taken using a camera, it does not rely on any physicality of the subject of those imageries. In this case, what's the point of doing so? And what does it imply? In search of answers to this question, I found that it could be used as a platform to explore our "hive mind" perception of concepts, ideas, and bias, and to present them in realistically convincing or utterly surreal ways.
In this piece, I chose the combination of human portrait arts and real-life cat photos - two categories that wouldn't normally come across each other - as my subject of synthesis. 5000+ images of human portraits were trained on StyleGAN, with an additional layer of 2000+ cat faces. Below are some samples of the generated cat portraits:
With the batch of synthesized images, a p5.js sketck was created to animate the images with a customized framerate, and turned them into a video.
Once the synthezied video was compiled, it was fed into a streamline of vocoders in Max/MSP to generate different "meow" sounds, which were eventually transformed into the notes of Beethoven's Sonata No. 8.
Cycling '74 Expo 2019 Performance
