Deep Meditations: Controlled navigation of latent space

Akten, Memo; Fiebrink, Rebecca and Grierson, Mick. 2018. 'Deep Meditations: Controlled navigation of latent space'. In: NeurIPS 2018 Workshop on Machine Learning for Creativity and Design. Montreal, Canada 8 December 2018. [Conference or Workshop Item]

[img]
Preview
Text
Deep_Meditations.pdf

Download (9MB) | Preview

Abstract or Description

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 discover and design trajectories in these high dimensional spaces, to construct stories, and produce time-based media such as videos—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 http://deepmeditations.ai.

Item Type:

Conference or Workshop Item (Poster)

Related URLs:

Departments, Centres and Research Units:

Computing
Computing > Embodied AudioVisual Interaction Group (EAVI)

Dates:

DateEvent
9 November 2018Accepted
8 December 2018Published

Event Location:

Montreal, Canada

Date range:

8 December 2018

Item ID:

25245

Date Deposited:

13 Dec 2018 12:17

Last Modified:

29 Apr 2020 17:01

URI:

https://research.gold.ac.uk/id/eprint/25245

View statistics for this item...

Edit Record Edit Record (login required)