VOID - Letters and Trees

28 April 2017 ● less than 1 min read ● 0 images

I shot this music video for my friends at Letters and Trees (http://www.lettersandtrees.com) in and around Tokyo last summer. The visual effect was mostly done using a neural network based on a modification of the inception architecture that was made famous by Google's DeepDream. The parameters used and the strength of the effect evolve during the video along with the character's progress.

There are no comments on this creation yet.

You can log in to post a comment.

About Max

Max Frenzel

I'm a researcher in Tokyo, Japan

Quantum physicist turned AI Researcher who loves to apply abstract maths to all sorts of creative projects.

See full profile

Welcome to Canvas Tokyo

Canvas is an online network for Tokyo's creative community. It's a place for professional and amateur creatives to show their skills, make new connections and find work.

Sign up to Canvas