Deep Meditations: Controlled navigation of latent space
This work addresses the challenge of providing meaningful human control in creative applications of deep generative models, such as story-telling and video production, which is incremental as it builds on existing generative models with a new interface method.
The paper tackles the problem of enabling creative exploration and navigation in the latent spaces of deep generative models, allowing users to discover and design trajectories for constructing stories and producing time-based media like videos with meaningful control over narrative.
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}.