Blackberry winter

Blackberry Winter compresses organic observations into code whilst articulating new logical concepts through movement. The project is an ongoing journey through the synthetic space of physical human nature. As an artwork, Blackberry Winter investigates the possibilities to identify motion as a continuous walk in an inapparent space of situations, blending the concepts of human and technological motion and body.



Project

The three resulting video screens ask questions on these two worlds that technology and humanity seem to define, their differences and similarities in the nature of impressions as well as the ongoing desire to digitize human actions and to humanize digital procedures. Fading into oneself and ever changing, the project stems from the idea to generate dance-like motion and choreography. Whilst floating through space, Blackberry Winter seeks to find the sweet spot between those worlds.

Technology

Blackberry Winter is a video triptych of artificial human motion in asymmetry: The artwork features three different choreographies of human bodies and their ongoing neural relationship in reference to each other, using a custom machine learning solution to weave spatial information into contemporary GAN technology. Using 120.000 human movements and moments of poses, the machine continuously learns whilst it moves through this space of possibilities. This particular movement through the possible poses at first sight looks like dance to the viewer, although the machine had no dance or movement in its source data, more so the dance sequences appear by themselves through the transition. All textures, colors and gradients are furthermore generated through the custom Generative Adversarial Network pipeline called RayGan, which could be described as a network trained with a curated dataset of visual artists.

COLLABORATORS

Art Direction: Christian Mio Loclair
AI Artist: Meredith Thomas
Executive Production: Celia Bugniot
Music: Christian Losert
Design: AJ Walsh