Project
We investigate the possibilities to identify motion as a continuous walk in a latent space of situations. Blackberry Winter is a triptych of artificial human motion in asymmetry. We developed three different choreographies of human bodies and their ongoing neural relationship in reference to each other, using our custom machine learning solution to weave spatial information into contemporary GAN technology.
Technology
We developed a custom Generative Adversarial Network pipeline called RayGan to teach our network a possibility space of human poses. The ongoing journey through this synthetic space of physical human nature, is then perceived as dance. The training data is generated by 120.000 postures of human bodies, yet it was never introduced to a sequence of movements or velocity. All textures, colors and gradients are furthermore generated through our own designer GAN. A network trained with a curated dataset of visual artists.
Background
The idea to generate dance like motion and choreography is a lifelong dream of mine. Coding and dancing since 1992, I always enjoyed the sense of both as well as their interplay. The idea to compress organic observations into code and the feeling to articulate new logical concepts through organic movements. To find a sweet spot between those worlds, which examines the nature of both impressions, is what motivated my ongoing desire to digitize human actions and to humanize digital procedures.
Collaborators
Art Direction: Christian Mio Loclair AI Artist: Meredith Thomas Executive Production: Celia Bugniot Music: Christian Losert Design: AJ Walsh
sources https://christianmioloclair.com/blackberrywinter