English

Deep Meditations: Controlled navigation of latent space

Computer Vision and Pattern Recognition 2020-03-03 v1 Human-Computer Interaction Machine Learning

Abstract

We introduce a method which allows users to creatively explore and navigate the vast latent spaces of deep generative models. Specifically, our method enables users to \textit{discover} and \textit{design} \textit{trajectories} in these high dimensional spaces, to construct stories, and produce time-based media such as videos---\textit{with meaningful control over narrative}. Our goal is to encourage and aid the use of deep generative models as a medium for creative expression and story telling with meaningful human control. Our method is analogous to traditional video production pipelines in that we use a conventional non-linear video editor with proxy clips, and conform with arrays of latent space vectors. Examples can be seen at \url{http://deepmeditations.ai}.

Keywords

Cite

@article{arxiv.2003.00910,
  title  = {Deep Meditations: Controlled navigation of latent space},
  author = {Memo Akten and Rebecca Fiebrink and Mick Grierson},
  journal= {arXiv preprint arXiv:2003.00910},
  year   = {2020}
}

Comments

Presented at the 2nd Workshop on Machine Learning for Creativity and Design at the Neural Information Processing Systems (NeurIPS) 2018 conference in Montreal

R2 v1 2026-06-23T14:00:24.150Z